ICML 2024 Schedule

The schedule for 2024 is still being finalized. Recheck this page again closer to the conference start date.

Filter Events

SUN 21 JUL

1 a.m.

Registration

(ends 8:00 AM)

4 a.m.

Expo Talk Demo:

AudioSeal: Proactive Detection of Voice Cloning with Localized Watermarking

(ends 5:00 AM)

Expo Talk Panel:

The Impact of Document Vectorisation, RAG, and Large Language Models in Financial Services: An insider view of how AI is set to change the way banks work

(ends 5:00 AM)

Expo Talk Panel:

Giving your Graph a Voice: Graph Representations and Large Language Models

(ends 5:00 AM)

Expo Talk Panel:

AutoGluon: AutoML at Your Fingertips

(ends 5:00 AM)

5 a.m.

Break:

Coffee Break

(ends 5:30 AM)

5:30 a.m.

Expo Workshop:

Run PyTorch Models On Device

(ends 7:30 AM)

Expo Talk Panel:

Accelerating research in Private Federated Learning with the pfl-research simulation framework

(ends 6:30 AM)

Expo Talk Panel:

Automated Evaluation of LLM responses

(ends 6:30 AM)

6:30 a.m.

Break:

Coffee Break

(ends 7:00 AM)

7 a.m.

Expo Talk Panel:

AI for software development at Google

(ends 8:00 AM)

Expo Talk Panel:

Merging Statistical, Causal, and Generative AI Techniques for Application Performance Monitoring

(ends 8:00 AM)

11:30 p.m.

Registration

(ends 9:00 AM)

MON 22 JUL

midnight

Workshop:

{Dis}Ability and Queer in AI Workshop

(ends 7:00 AM)

Workshop:

LatinX in AI (LXAI) Research Workshop

(ends 7:00 AM)

Break:

Coffee Break

(ends 12:30 AM)

12:30 a.m.

Tutorial:

Data Attribution at Scale

(ends 2:30 AM)

Tutorial:

Towards Efficient Generative Large Language Model Serving: A Tutorial from Algorithms to Systems

(ends 2:30 AM)

Tutorial:

Strategic ML: How to Learn With Data That ‘Behaves’

(ends 2:30 AM)

Tutorial:

Graph Learning: Principles, Challenges, and Open Directions

(ends 2:30 AM)

2:30 a.m.

Break:

Hosted Lunch

(ends 4:00 AM)

4 a.m.

Tutorial:

Mixture-of-Experts in the Era of LLMs: A New Odyssey

(ends 6:00 AM)

Tutorial:

Understanding the Role of Large Language Models in Planning

(ends 6:00 AM)

Tutorial:

Distribution-Free Predictive Uncertainty Quantification: Strengths and Limits of Conformal Prediction

(ends 6:00 AM)

Tutorial:

Foundations of Data-efficient Machine Learning

(ends 6:00 AM)

6 a.m.

Break:

Coffee Break

(ends 6:30 AM)

6:30 a.m.

Tutorial:

Physics of Language Models

(ends 8:30 AM)

Tutorial:

Challenges in Language Model Evaluations

(ends 8:30 AM)

Tutorial:

Convex Analysis at Infinity: An Introduction to Astral Space

(ends 8:30 AM)

Tutorial:

Neural Operator Learning

(ends 8:30 AM)

7 a.m.

Affinity Joint Poster Session [7:00-8:30]

(ends 8:30 AM)

8:30 a.m.

Break:

Coffee Break

(ends 9:00 AM)

9 a.m.

Invited Talk:

TBD Opening Remarks

(ends 10:00 AM)

10 a.m.

Reception:

Welcome Reception

(ends 11:15 AM)

11 p.m.

Registration

(ends 9:00 AM)

TUE 23 JUL

midnight

Invited Talk:

Soumith Chintala

(ends 1:00 AM)

1 a.m.

Break:

Coffee Break

(ends 1:30 AM)

1:30 a.m.

Oral 1x Positions on How We Do Machine Learning Research [1:30-2:30]

Orals 1:30-2:30

[1:30] Position: Embracing Negative Results in Machine Learning

[1:45] Position: A Safe Harbor for AI Evaluation and Red Teaming

[2:00] Position: Considerations for Differentially Private Learning with Large-Scale Public Pretraining

[2:15] Position: Beyond Personhood: Agency, Accountability, and the Limits of Anthropomorphic Ethical Analysis

(ends 2:30 AM)

Oral 1x Alignment [1:30-2:30]

Orals 1:30-2:30

[1:30] Debating with More Persuasive LLMs Leads to More Truthful Answers

[1:45] Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision

[2:00] A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity

[2:15] Is DPO Superior to PPO for LLM Alignment? A Comprehensive Study

(ends 2:30 AM)

Oral 1x Clustering [1:30-2:30]

Orals 1:30-2:30

[1:30] LSEnet: Lorentz Structural Entropy Neural Network for Deep Graph Clustering

[1:45] Image Clustering with External Guidance

[2:00] Making Old Things New: A Unified Algorithm for Differentially Private Clustering

[2:15] Pruned Pivot: Correlation Clustering Algorithm for Dynamic, Parallel, and Local Computation Models

(ends 2:30 AM)

Oral 1x Video [1:30-2:30]

Orals 1:30-2:30

[1:30] Genie: Generative Interactive Environments

[1:45] Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization

[2:00] Video-of-Thought: Step-by-Step Video Reasoning from Perception to Cognition

[2:15] VideoPoet: A Large Language Model for Zero-Shot Video Generation

(ends 2:30 AM)

Oral 1x Applications in Biology and Chemistry [1:30-2:30]

Orals 1:30-2:30

[1:30] MorphGrower: A Synchronized Layer-by-layer Growing Approach for Plausible Neuronal Morphology Generation

[1:45] EquiPocket: an E(3)-Equivariant Geometric Graph Neural Network for Ligand Binding Site Prediction

[2:00] Expressivity and Generalization: Fragment-Biases for Molecular GNNs

[2:15] Preference Optimization for Molecule Synthesis with Conditional Residual Energy-based Models

(ends 2:30 AM)

Oral 1x Time Series [1:30-2:30]

Orals 1:30-2:30

[1:30] SparseTSF: Modeling Long-term Time Series Forecasting with *1k* Parameters

[1:45] Arrows of Time for Large Language Models

[2:00] Unified Training of Universal Time Series Forecasting Transformers

[2:15] SAMformer: Unlocking the Potential of Transformers in Time Series Forecasting with Sharpness-Aware Minimization and Channel-Wise Attention

(ends 2:30 AM)

2:30 a.m.

Poster Session 1 [2:30-4:00]

Posters 2:30-4:00

Value-Evolutionary-Based Reinforcement Learning

Learning Temporal Distances: Contrastive Successor Features Can Provide a Metric Structure for Decision-Making

In-context Convergence of Transformers

Feature Attribution with Necessity and Sufficiency via Dual-stage Perturbation Test for Causal Explanation

Learning from Students: Applying t-Distributions to Explore Accurate and Efficient Formats for LLMs

Pruner-Zero: Evolving Symbolic Pruning Metric From Scratch for Large Language Models

Minimum-Norm Interpolation Under Covariate Shift

SLAB: Efficient Transformers with Simplified Linear Attention and Progressive Re-parameterized Batch Normalization

Adversarial Robustness Limits via Scaling-Law and Human-Alignment Studies

Behavior Generation with Latent Actions

EvoRainbow: Combining Improvements in Evolutionary Reinforcement Learning for Policy Search

Understanding MLP-Mixer as a wide and sparse MLP

Private Gradient Descent for Linear Regression: Tighter Error Bounds and Instance-Specific Uncertainty Estimation

Privacy-Preserving Instructions for Aligning Large Language Models

KISA: A Unified Keyframe Identifier and Skill Annotator for Long-Horizon Robotics Demonstrations

A Provably Effective Method for Pruning Experts in Fine-tuned Sparse Mixture-of-Experts

Adaptively Learning to Select-Rank in Online Platforms

Can AI Assistants Know What They Don't Know?

Unsupervised Evaluation of Code LLMs with Round-Trip Correctness

Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference

BWS: Best Window Selection Based on Sample Scores for Data Pruning across Broad Ranges

Uniformly Stable Algorithms for Adversarial Training and Beyond

Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AI

Towards Neural Architecture Search through Hierarchical Generative Modeling

Adaptive Advantage-Guided Policy Regularization for Offline Reinforcement Learning

Hyperbolic Geometric Latent Diffusion Model for Graph Generation

Outlier-robust Kalman Filtering through Generalised Bayes

Provably Scalable Black-Box Variational Inference with Structured Variational Families

Robust Stable Spiking Neural Networks

Dynamic Spectral Clustering with Provable Approximation Guarantee

Accelerating PDE Data Generation via Differential Operator Action in Solution Space

GeoAB: Towards Realistic Antibody Design and Reliable Affinity Maturation

Expressivity and Generalization: Fragment-Biases for Molecular GNNs

Purify Unlearnable Examples via Rate-Constrained Variational Autoencoders

RankSEG: A Consistent Ranking-based Framework for Segmentation

S3O: A Dual-Phase Approach for Reconstructing Dynamic Shape and Skeleton of Articulated Objects from Single Monocular Video

Towards Scalable and Versatile Weight Space Learning

On the Minimal Degree Bias in Generalization on the Unseen for non-Boolean Functions

An Efficient Self-Learning Framework For Interactive Spoken Dialog Systems

Learning in Deep Factor Graphs with Gaussian Belief Propagation

LSEnet: Lorentz Structural Entropy Neural Network for Deep Graph Clustering

Evolution-Inspired Loss Functions for Protein Representation Learning

Byzantine Resilient and Fast Federated Few-Shot Learning

Pluvial Flood Emulation with Hydraulics-informed Message Passing

Gated Linear Attention Transformers with Hardware-Efficient Training

EiG-Search: Generating Edge-Induced Subgraphs for GNN Explanation in Linear Time

Reinforcement Learning and Regret Bounds for Admission Control

Online Learning in Betting Markets: Profit versus Prediction

Using Left and Right Brains Together: Towards Vision and Language Planning

Representation Surgery: Theory and Practice of Affine Steering

SSL4Q: Semi-Supervised Learning of Quantum Data with Application to Quantum State Classification

Causal Inference out of Control: Estimating Performativity without Treatment Randomization

Neighboring Perturbations of Knowledge Editing on Large Language Models

Private Heterogeneous Federated Learning Without a Trusted Server Revisited: Error-Optimal and Communication-Efficient Algorithms for Convex Losses

GeoMFormer: A General Architecture for Geometric Molecular Representation Learning

Defense against Model Extraction Attack by Bayesian Active Watermarking

Evaluating and Analyzing Relationship Hallucinations in Large Vision-Language Models

SeMOPO: Learning High-quality Model and Policy from Low-quality Offline Visual Datasets

Hierarchical Neural Operator Transformer with Learnable Frequency-aware Loss Prior for Arbitrary-scale Super-resolution

Classification under Nuisance Parameters and Generalized Label Shift in Likelihood-Free Inference

Diagnosing the Compositional Knowledge of Vision Language Models from a Game-Theoretic View

NExT-Chat: An LMM for Chat, Detection and Segmentation

Model Alignment as Prospect Theoretic Optimization

Latent Noise Segmentation: How Neural Noise Leads to the Emergence of Segmentation and Grouping

Major-Minor Mean Field Multi-Agent Reinforcement Learning

Making Old Things New: A Unified Algorithm for Differentially Private Clustering

A Persuasive Approach to Combating Misinformation

Triadic-OCD: Asynchronous Online Change Detection with Provable Robustness, Optimality, and Convergence

Interpretable Deep Clustering for Tabular Data

Towards General Algorithm Discovery for Combinatorial Optimization: Learning Symbolic Branching Policy from Bipartite Graph

Principled Gradient-Based MCMC for Conditional Sampling of Text

Is In-Context Learning in Large Language Models Bayesian? A Martingale Perspective

Learning to Explore in POMDPs with Informational Rewards

Prometheus: Out-of-distribution Fluid Dynamics Modeling with Disentangled Graph ODE

Fine-tuning Reinforcement Learning Models is Secretly a Forgetting Mitigation Problem

Position: Categorical Deep Learning is an Algebraic Theory of All Architectures

MusicFlow: Cascaded Flow Matching for Text Guided Music Generation

Open-Vocabulary Calibration for Fine-tuned CLIP

GaussianPro: 3D Gaussian Splatting with Progressive Propagation

An Interpretable Evaluation of Entropy-based Novelty of Generative Models

Towards Global Optimality for Practical Average Reward Reinforcement Learning without Mixing Time Oracles

EquiPocket: an E(3)-Equivariant Geometric Graph Neural Network for Ligand Binding Site Prediction

Prompt-guided Precise Audio Editing with Diffusion Models

Pruned Pivot: Correlation Clustering Algorithm for Dynamic, Parallel, and Local Computation Models

A Circuit Domain Generalization Framework for Efficient Logic Synthesis in Chip Design

On the Convergence of Projected Bures-Wasserstein Gradient Descent under Euclidean Strong Convexity

MorphGrower: A Synchronized Layer-by-layer Growing Approach for Plausible Neuronal Morphology Generation

Unified Training of Universal Time Series Forecasting Transformers

Privately Learning Smooth Distributions on the Hypercube by Projections

EvGGS: A Collaborative Learning Framework for Event-based Generalizable Gaussian Splatting

Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models

Two Fists, One Heart: Multi-Objective Optimization Based Strategy Fusion for Long-tailed Learning

Learning to Play Atari in a World of Tokens

Classification Under Strategic Self-Selection

Implicit Representations via Operator Learning

Covert Malicious Finetuning: Challenges in Safeguarding LLM Adaptation

Logistic Variational Bayes Revisited

VoroNav: Voronoi-based Zero-shot Object Navigation with Large Language Model

CoLoRA: Continuous low-rank adaptation for reduced implicit neural modeling of parameterized partial differential equations

ODIM: Outlier Detection via Likelihood of Under-Fitted Generative Models

Generative Enzyme Design Guided by Functionally Important Sites and Small-Molecule Substrates

Optimal Eye Surgeon: Finding image priors through sparse generators at initialization

Hypergraph-enhanced Dual Semi-supervised Graph Classification

Causal Bandits: The Pareto Optimal Frontier of Adaptivity, a Reduction to Linear Bandits, and Limitations around Unknown Marginals

Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities

Rényi Pufferfish Privacy: General Additive Noise Mechanisms and Privacy Amplification by Iteration via Shift Reduction Lemmas

Bifurcated Attention for Single-Context Large-Batch Sampling

Tuning-free Estimation and Inference of Cumulative Distribution Function under Local Differential Privacy

Position: Application-Driven Innovation in Machine Learning

Can a Few Decide for Many? The Metric Distortion of Sortition

Graph Distillation with Eigenbasis Matching

Lookbehind-SAM: k steps back, 1 step forward

Towards an Understanding of Stepwise Inference in Transformers: A Synthetic Graph Navigation Model

Think Before You Act: Decision Transformers with Working Memory

Graph Adversarial Diffusion Convolution

Binning as a Pretext Task: Improving Self-Supervised Learning in Tabular Domains

Overcoming Data and Model heterogeneities in Decentralized Federated Learning via Synthetic Anchors

Generalizing Orthogonalization for Models with Non-Linearities

Memory Consolidation Enables Long-Context Video Understanding

Convergence of Online Learning Algorithm for a Mixture of Multiple Linear Regressions

Modeling Caption Diversity in Contrastive Vision-Language Pretraining

Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibration

Equivariant Deep Weight Space Alignment

Deep Stochastic Mechanics

First-Order Manifold Data Augmentation for Regression Learning

Failures Are Fated, But Can Be Faded: Characterizing and Mitigating Unwanted Behaviors in Large-Scale Vision and Language Models

Constrained Exploration via Reflected Replica Exchange Stochastic Gradient Langevin Dynamics

Delving into the Convergence of Generalized Smooth Minimax Optimization

Online Non-stochastic Control with Partial Feedback

Learning Coverage Paths in Unknown Environments with Deep Reinforcement Learning

Two Heads are Actually Better than One: Towards Better Adversarial Robustness via Transduction and Rejection

Confidence-aware Contrastive Learning for Selective Classification

Q-Star Meets Scalable Posterior Sampling: Bridging Theory and Practice via HyperAgent

Exploring the LLM Journey from Cognition to Expression with Linear Representations

Self-Rewarding Language Models

On the Duality Between Sharpness-Aware Minimization and Adversarial Training

Optimal Exact Recovery in Semi-Supervised Learning: A Study of Spectral Methods and Graph Convolutional Networks

A Unified View of FANOVA: A Comprehensive Bayesian Framework for Component Selection and Estimation

Cluster-Aware Similarity Diffusion for Instance Retrieval

Directly Denoising Diffusion Models

Linear Explanations for Individual Neurons

Membership Inference Attacks on Diffusion Models via Quantile Regression

Improving Context Understanding in Multimodal Large Language Models via Multimodal Composition Learning

Iterative Regularized Policy Optimization with Imperfect Demonstrations

Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model

Position: Beyond Personhood: Agency, Accountability, and the Limits of Anthropomorphic Ethical Analysis

CKGConv: General Graph Convolution with Continuous Kernels

Scribble-Supervised Semantic Segmentation with Prototype-based Feature Augmentation

Position: Quo Vadis, Unsupervised Time Series Anomaly Detection?

Two Stones Hit One Bird: Bilevel Positional Encoding for Better Length Extrapolation

No Dimensional Sampling Coresets for Classification

Rethinking Decision Transformer via Hierarchical Reinforcement Learning

MOKD: Cross-domain Finetuning for Few-shot Classification via Maximizing Optimized Kernel Dependence

Neurodegenerative Brain Network Classification via Adaptive Diffusion with Temporal Regularization

Unlock the Cognitive Generalization of Deep Reinforcement Learning via Granular Ball Representation

Dynamic Anisotropic Smoothing for Noisy Derivative-Free Optimization

Relational DNN Verification With Cross Executional Bound Refinement

ProtoGate: Prototype-based Neural Networks with Global-to-local Feature Selection for Tabular Biomedical Data

In-context Learning on Function Classes Unveiled for Transformers

Learning Causal Relations from Subsampled Time Series with Two Time-Slices

Distribution Alignment Optimization through Neural Collapse for Long-tailed Classification

Bayesian Uncertainty for Gradient Aggregation in Multi-Task Learning

An Intrinsic Vector Heat Network

VQDNA: Unleashing the Power of Vector Quantization for Multi-Species Genomic Sequence Modeling

Dealing With Unbounded Gradients in Stochastic Saddle-point Optimization

EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty

Perturb-and-Project: Differentially Private Similarities and Marginals

BOtied: Multi-objective Bayesian optimization with tied multivariate ranks

FedSC: Provable Federated Self-supervised Learning with Spectral Contrastive Objective over Non-i.i.d. Data

Sign is Not a Remedy: Multiset-to-Multiset Message Passing for Learning on Heterophilic Graphs

Split-and-Denoise: Protect large language model inference with local differential privacy

Reshape and Adapt for Output Quantization (RAOQ): Quantization-aware Training for In-memory Computing Systems

Lyapunov-stable Neural Control for State and Output Feedback: A Novel Formulation

QuIP$\#$: Even Better LLM Quantization with Hadamard Incoherence and Lattice Codebooks

Learning to Intervene on Concept Bottlenecks

Contextual Feature Selection with Conditional Stochastic Gates

GiLOT: Interpreting Generative Language Models via Optimal Transport

Neural Diffusion Models

Fault Tolerant ML: Efficient Meta-Aggregation and Synchronous Training

Evaluation of Test-Time Adaptation Under Computational Time Constraints

On Least Square Estimation in Softmax Gating Mixture of Experts

Enhancing Size Generalization in Graph Neural Networks through Disentangled Representation Learning

Bayesian Design Principles for Offline-to-Online Reinforcement Learning

Synergistic Integration of Coordinate Network and Tensorial Feature for Improving Neural Radiance Fields from Sparse Inputs

Improving Interpretation Faithfulness for Vision Transformers

Taylor Videos for Action Recognition

Repeat After Me: Transformers are Better than State Space Models at Copying

OT-CLIP: Understanding and Generalizing CLIP via Optimal Transport

Theoretical insights for diffusion guidance: A case study for Gaussian mixture models

Information Flow in Self-Supervised Learning

Tight Partial Identification of Causal Effects with Marginal Distribution of Unmeasured Confounders

FlashST: A Simple and Universal Prompt-Tuning Framework for Traffic Prediction

Replicable Learning of Large-Margin Halfspaces

In-Context Sharpness as Alerts: An Inner Representation Perspective for Hallucination Mitigation

Language Models as Semantic Indexers

Multi-Region Markovian Gaussian Process: An Efficient Method to Discover Directional Communications Across Multiple Brain Regions

Bayesian Power Steering: An Effective Approach for Domain Adaptation of Diffusion Models

Parsimonious Learning-Augmented Approximations for Dense Instances of $\mathcal{NP}$-hard Problems

UGrid: An Efficient-And-Rigorous Neural Multigrid Solver for Linear PDEs

KernelWarehouse: Rethinking the Design of Dynamic Convolution

IOI: Invisible One-Iteration Adversarial Attack on No-Reference Image- and Video-Quality Metrics

Moreau Envelope for Nonconvex Bi-Level Optimization: A Single-Loop and Hessian-Free Solution Strategy

Optimal bounds for $\ell_p$ sensitivity sampling via $\ell_2$ augmentation

Position: Is machine learning good or bad for the natural sciences?

HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal

Going beyond Compositions, DDPMs Can Produce Zero-Shot Interpolations

Quality-Diversity Actor-Critic: Learning High-Performing and Diverse Behaviors via Value and Successor Features Critics

Discovering Symmetry Breaking in Physical Systems with Relaxed Group Convolution

Allocation Requires Prediction Only if Inequality Is Low

InstructZero: Efficient Instruction Optimization for Black-Box Large Language Models

Thermometer: Towards Universal Calibration for Large Language Models

Probabilistic Modeling of Interpersonal Coordination Processes

Probabilistic Subgoal Representations for Hierarchical Reinforcement Learning

Stabilizing Policy Gradients for Stochastic Differential Equations via Consistency with Perturbation Process

Human vs. Generative AI in Content Creation Competition: Symbiosis or Conflict?

Understanding the Learning Dynamics of Alignment with Human Feedback

Non-Asymptotic Analysis for Single-Loop (Natural) Actor-Critic with Compatible Function Approximation

Structure-based drug design by denoising voxel grids

Using AI Uncertainty Quantification to Improve Human Decision-Making

Harmonic Self-Conditioned Flow Matching for joint Multi-Ligand Docking and Binding Site Design

Naive Bayes Classifiers over Missing Data: Decision and Poisoning

Layerwise Change of Knowledge in Neural Networks

Feature Contamination: Neural Networks Learn Uncorrelated Features and Fail to Generalize

From Generalization Analysis to Optimization Designs for State Space Models

Nesting Particle Filters for Experimental Design in Dynamical Systems

Reflected Flow Matching

Adversarially Robust Hypothesis Transfer Learning

Debating with More Persuasive LLMs Leads to More Truthful Answers

Reward Model Learning vs. Direct Policy Optimization: A Comparative Analysis of Learning from Human Preferences

Graph Positional and Structural Encoder

Pairwise Alignment Improves Graph Domain Adaptation

One Prompt is not Enough: Automated Construction of a Mixture-of-Expert Prompts

Online Linear Regression in Dynamic Environments via Discounting

CrossGET: Cross-Guided Ensemble of Tokens for Accelerating Vision-Language Transformers

ByMI: Byzantine Machine Identification with False Discovery Rate Control

Learning Modality Knowledge Alignment for Cross-Modality Transfer

Prompt-based Visual Alignment for Zero-shot Policy Transfer

Bipartite Matching in Massive Graphs: A Tight Analysis of EDCS

Unveiling the Dynamics of Information Interplay in Supervised Learning

Robustly Learning Single-Index Models via Alignment Sharpness

Differentiable Combinatorial Scheduling at Scale

IIANet: An Intra- and Inter-Modality Attention Network for Audio-Visual Speech Separation

Combinatorial Multivariant Multi-Armed Bandits with Applications to Episodic Reinforcement Learning and Beyond

Quantum Implicit Neural Representations

CarbonNovo: Joint Design of Protein Structure and Sequence Using a Unified Energy-based Model

Mitigating Oversmoothing Through Reverse Process of GNNs for Heterophilic Graphs

Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization

Scalable Online Exploration via Coverability

IM-Unpack: Training and Inference with Arbitrarily Low Precision Integers

Arrows of Time for Large Language Models

On the Implicit Bias of Adam

Exploration and Anti-Exploration with Distributional Random Network Distillation

Machine Vision Therapy: Multimodal Large Language Models Can Enhance Visual Robustness via Denoising In-Context Learning

One for All: A Universal Generator for Concept Unlearnability via Multi-Modal Alignment

Implicit Bias of AdamW: $\ell_\infty$-Norm Constrained Optimization

Position: A Safe Harbor for AI Evaluation and Red Teaming

Human-like Category Learning by Injecting Ecological Priors from Large Language Models into Neural Networks

Denoising Autoregressive Representation Learning

DNCs Require More Planning Steps

Position: Considerations for Differentially Private Learning with Large-Scale Public Pretraining

FESSNC: Fast Exponentially Stable and Safe Neural Controller

Provable Contrastive Continual Learning

Neural operators meet conjugate gradients: The FCG-NO method for efficient PDE solving

Enforcing Constraints in RNA Secondary Structure Predictions: A Post-Processing Framework Based on the Assignment Problem

Nonparametric Teaching of Implicit Neural Representations

HelmFluid: Learning Helmholtz Dynamics for Interpretable Fluid Prediction

Open Ad Hoc Teamwork with Cooperative Game Theory

KnowFormer: Revisiting Transformers for Knowledge Graph Reasoning

Rethinking DP-SGD in Discrete Domain: Exploring Logistic Distribution in the Realm of signSGD

Protein Conformation Generation via Force-Guided SE(3) Diffusion Models

Genie: Generative Interactive Environments

Unbiased Multi-Label Learning from Crowdsourced Annotations

Risk-Sensitive Reward-Free Reinforcement Learning with CVaR

VideoPoet: A Large Language Model for Zero-Shot Video Generation

DFD: Distillng the Feature Disparity Differently for Detectors

On the Diminishing Returns of Width for Continual Learning

Enhancing Implicit Shape Generators Using Topological Regularizations

BadPart: Unified Black-box Adversarial Patch Attacks against Pixel-wise Regression Tasks

Rethinking Independent Cross-Entropy Loss For Graph-Structured Data

OODRobustBench: a Benchmark and Large-Scale Analysis of Adversarial Robustness under Distribution Shift

IW-GAE: Importance weighted group accuracy estimation for improved calibration and model selection in unsupervised domain adaptation

Score-Based Causal Discovery of Latent Variable Causal Models

CF-OPT: Counterfactual Explanations for Structured Prediction

From Inverse Optimization to Feasibility to ERM

On the Emergence of Cross-Task Linearity in Pretraining-Finetuning Paradigm

Position: Levels of AGI for Operationalizing Progress on the Path to AGI

Efficient Contextual Bandits with Uninformed Feedback Graphs

From Fourier to Neural ODEs: Flow Matching for Modeling Complex Systems

Compositional Few-Shot Class-Incremental Learning

Fine-grained Local Sensitivity Analysis of Standard Dot-Product Self-Attention

Position: Embracing Negative Results in Machine Learning

Meta Evidential Transformer for Few-Shot Open-Set Recognition

MoMo: Momentum Models for Adaptive Learning Rates

Sparse-IFT: Sparse Iso-FLOP Transformations for Maximizing Training Efficiency

TimeMIL: Advancing Multivariate Time Series Classification via a Time-aware Multiple Instance Learning

Box Facets and Cut Facets of Lifted Multicut Polytopes

LEVI: Generalizable Fine-tuning via Layer-wise Ensemble of Different Views

An Independence-promoting Loss for Music Generation with Language Models

Exploration-Driven Policy Optimization in RLHF: Theoretical Insights on Efficient Data Utilization

Generalized Preference Optimization: A Unified Approach to Offline Alignment

Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision

Generalization to New Sequential Decision Making Tasks with In-Context Learning

Counterfactual Image Editing

Overcoming Saturation in Density Ratio Estimation by Iterated Regularization

$S^2$IP-LLM: Semantic Space Informed Prompt Learning with LLM for Time Series Forecasting

Two Heads Are Better Than One: Boosting Graph Sparse Training via Semantic and Topological Awareness

HAMLET: Graph Transformer Neural Operator for Partial Differential Equations

Stereographic Spherical Sliced Wasserstein Distances

Positive Concave Deep Equilibrium Models

From Words to Actions: Unveiling the Theoretical Underpinnings of LLM-Driven Autonomous Systems

Energy-based Backdoor Defense without Task-Specific Samples and Model Retraining

Incremental Topological Ordering and Cycle Detection with Predictions

Compression of Structured Data with Autoencoders: Provable Benefit of Nonlinearities and Depth

Hybrid Inverse Reinforcement Learning

A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity

TVE: Learning Meta-attribution for Transferable Vision Explainer

On Computational Limits of Modern Hopfield Models: A Fine-Grained Complexity Analysis

Provable Benefits of Local Steps in Heterogeneous Federated Learning for Neural Networks: A Feature Learning Perspective

Switched Flow Matching: Eliminating Singularities via Switching ODEs

Enhancing Trajectory Prediction through Self-Supervised Waypoint Distortion Prediction

SparseTSF: Modeling Long-term Time Series Forecasting with *1k* Parameters

Fair Classification with Partial Feedback: An Exploration-Based Data Collection Approach

Estimating Canopy Height at Scale

Diffusion Language Models Are Versatile Protein Learners

Data Poisoning Attacks against Conformal Prediction

Efficient Black-box Adversarial Attacks via Bayesian Optimization Guided by a Function Prior

DOGE: Domain Reweighting with Generalization Estimation

Translation Equivariant Transformer Neural Processes

On Gradient-like Explanation under a Black-box Setting: When Black-box Explanations Become as Good as White-box

Potential Based Diffusion Motion Planning

Enhancing Vision Transformer: Amplifying Non-Linearity in Feedforward Network Module

RAUCA: A Novel Physical Adversarial Attack on Vehicle Detectors via Robust and Accurate Camouflage Generation

Residual-Conditioned Optimal Transport: Towards Structure-Preserving Unpaired and Paired Image Restoration

ACPO: A Policy Optimization Algorithm for Average MDPs with Constraints

DeepPolar: Inventing Nonlinear Large-Kernel Polar Codes via Deep Learning

Accelerating Look-ahead in Bayesian Optimization: Multilevel Monte Carlo is All you Need

Learning Multiple Secrets in Mastermind

Efficient World Models with Context-Aware Tokenization

GeminiFusion: Efficient Pixel-wise Multimodal Fusion for Vision Transformer

Pragmatic Feature Preferences: Learning Reward-Relevant Preferences from Human Input

Fast Adversarial Attacks on Language Models In One GPU Minute

Size-invariance Matters: Rethinking Metrics and Losses for Imbalanced Multi-object Salient Object Detection

Provably Efficient Partially Observable Risk-sensitive Reinforcement Learning with Hindsight Observation

Uniform Memory Retrieval with Larger Capacity for Modern Hopfield Models

Encodings for Prediction-based Neural Architecture Search

Fundamental Benefit of Alternating Updates in Minimax Optimization

ArtWhisperer: A Dataset for Characterizing Human-AI Interactions in Artistic Creations

Observable Propagation: Uncovering Feature Vectors in Transformers

The Merit of River Network Topology for Neural Flood Forecasting

PARCv2: Physics-aware Recurrent Convolutional Neural Networks for Spatiotemporal Dynamics Modeling

WAVES: Benchmarking the Robustness of Image Watermarks

GistScore: Learning Better Representations for In-Context Example Selection with Gist Bottlenecks

Random Latent Exploration for Deep Reinforcement Learning

Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data

Image Clustering with External Guidance

Stochastic Gradient Flow Dynamics of Test Risk and its Exact Solution for Weak Features

ReDiffuser: Reliable Decision-Making Using a Diffuser with Confidence Estimation

Effects of Exponential Gaussian Distribution on (Double Sampling) Randomized Smoothing

Invariant Risk Minimization Is A Total Variation Model

Risk-Sensitive Policy Optimization via Predictive CVaR Policy Gradient

Aligning Transformers with Weisfeiler-Leman

Finite Smoothing Algorithm for High-Dimensional Support Vector Machines and Quantile Regression

Online bipartite matching with imperfect advice

Hyperbolic Optimizer as a Dynamical System

A New Computationally Efficient Algorithm to solve Feature Selection for Functional Data Classification in High-dimensional Spaces

The Perception-Robustness Tradeoff in Deterministic Image Restoration

Sampling-based Multi-dimensional Recalibration

Regularizing with Pseudo-Negatives for Continual Self-Supervised Learning

New Sample Complexity Bounds for Sample Average Approximation in Heavy-Tailed Stochastic Programming

Probability Distribution of Hypervolume Improvement in Bi-objective Bayesian Optimization

A Theory of Non-Linear Feature Learning with One Gradient Step in Two-Layer Neural Networks

MOMENT: A Family of Open Time-series Foundation Models

Data-Efficient Learning via Clustering-Based Sensitivity Sampling: Foundation Models and Beyond

Implicit meta-learning may lead language models to trust more reliable sources

In-Context Principle Learning from Mistakes

Generating In-Distribution Proxy Graphs for Explaining Graph Neural Networks

Chasing Convex Functions with Long-term Constraints

MaSS: Multi-attribute Selective Suppression for Utility-preserving Data Transformation from an Information-theoretic Perspective

Scalable Wasserstein Gradient Flow for Generative Modeling through Unbalanced Optimal Transport

Dense Reward for Free in Reinforcement Learning from Human Feedback

Scaling Down Deep Learning with MNIST-1D

Position: Near to Mid-term Risks and Opportunities of Open-Source Generative AI

Ai-sampler: Adversarial Learning of Markov kernels with involutive maps

$\texttt{MoE-RBench}$: Towards Building Reliable Language Models with Sparse Mixture-of-Experts

Out of the Ordinary: Spectrally Adapting Regression for Covariate Shift

Double-Step Alternating Extragradient with Increasing Timescale Separation for Finding Local Minimax Points: Provable Improvements

MMPareto: Boosting Multimodal Learning with Innocent Unimodal Assistance

A Sparsity Principle for Partially Observable Causal Representation Learning

Position: Do Not Explain Vision Models Without Context

Isometric Representation Learning for Disentangled Latent Space of Diffusion Models

Parameter-Efficient Fine-Tuning with Controls

Mastering Robot Manipulation with Multimodal Prompts through Pretraining and Multi-task Fine-tuning

TabLog: Test-Time Adaptation for Tabular Data Using Logic Rules

High-Dimensional Kernel Methods under Covariate Shift: Data-Dependent Implicit Regularization

Align Your Steps: Optimizing Sampling Schedules in Diffusion Models

DiffFPR: Diffusion Prior for Oversampled Fourier Phase Retrieval

Deconstructing the Goldilocks Zone of Neural Network Initialization

Generalization Bounds for Heavy-Tailed SDEs through the Fractional Fokker-Planck Equation

MuxServe: Flexible Spatial-Temporal Multiplexing for Multiple LLM Serving

Differentiable Weightless Neural Networks

An Explicit Frame Construction for Normalizing 3D Point Clouds

Quality Diversity through Human Feedback: Towards Open-Ended Diversity-Driven Optimization

Scene Graph Generation Strategy with Co-occurrence Knowledge and Learnable Term Frequency

On the Feasibility of Single-Pass Full-Capacity Learning in Linear Threshold Neurons with Binary Input Vectors

Barrier Algorithms for Constrained Non-Convex Optimization

When Do Skills Help Reinforcement Learning? A Theoretical Analysis of Temporal Abstractions

High-Order Contrastive Learning with Fine-grained Comparative Levels for Sparse Ordinal Tensor Completion

Incentivized Learning in Principal-Agent Bandit Games

TIC-TAC: A Framework For Improved Covariance Estimation In Deep Heteroscedastic Regression

Self-Consistency Training for Density-Functional-Theory Hamiltonian Prediction

Solving Poisson Equations using Neural Walk-on-Spheres

AlphaFold Meets Flow Matching for Generating Protein Ensembles

An Iterative Min-Min Optimization Method for Sparse Bayesian Learning

Improved Dimensionality Dependence for Zeroth-Order Optimisation over Cross-Polytopes

SLOG: An Inductive Spectral Graph Neural Network Beyond Polynomial Filter

ELTA: An Enhancer against Long-Tail for Aesthetics-oriented Models

Scaling Tractable Probabilistic Circuits: A Systems Perspective

RoboGen: Towards Unleashing Infinite Data for Automated Robot Learning via Generative Simulation

GeoReasoner: Geo-localization with Reasoning in Street Views using a Large Vision-Language Model

BiE: Bi-Exponent Block Floating-Point for Large Language Models Quantization

Exploiting Negative Samples: A Catalyst for Cohort Discovery in Healthcare Analytics

Double Momentum Method for Lower-Level Constrained Bilevel Optimization

Differentially Private Synthetic Data via Foundation Model APIs 2: Text

OxyGenerator: Reconstructing Global Ocean Deoxygenation Over a Century with Deep Learning

Efficient Algorithms for Sum-Of-Minimum Optimization

An Information-Theoretic Analysis of In-Context Learning

Understanding Finetuning for Factual Knowledge Extraction

Mathematical Framework for Online Social Media Auditing

Submodular framework for structured-sparse optimal transport

MLIP: Efficient Multi-Perspective Language-Image Pretraining with Exhaustive Data Utilization

KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache

Generalized Smooth Variational Inequalities: Methods with Adaptive Stepsizes

Preference Optimization for Molecule Synthesis with Conditional Residual Energy-based Models

Learning Low-dimensional Latent Dynamics from High-dimensional Observations: Non-asymptotics and Lower Bounds

Learning the Target Network in Function Space

MS$^3$D: A RG Flow-Based Regularization for GAN Training with Limited Data

Is DPO Superior to PPO for LLM Alignment? A Comprehensive Study

Analyzing $D^\alpha$ seeding for $k$-means

Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads

On Online Experimentation without Device Identifiers

Diffusion Tempering Improves Parameter Estimation with Probabilistic Integrators for Ordinary Differential Equations

Positional Knowledge is All You Need: Position-induced Transformer (PiT) for Operator Learning

OptiMUS: Scalable Optimization Modeling with (MI)LP Solvers and Large Language Models

Towards efficient deep spiking neural networks construction with spiking activity based pruning

Language Generation with Strictly Proper Scoring Rules

Parameter-Efficient Fine-Tuning with Discrete Fourier Transform

A fast algorithm to simulate nonlinear resistive networks

Graph Automorphism Group Equivariant Neural Networks

FedLMT: Tackling System Heterogeneity of Federated Learning via Low-Rank Model Training with Theoretical Guarantees

Embarrassingly Parallel GFlowNets

Small-loss Adaptive Regret for Online Convex Optimization

SAMformer: Unlocking the Potential of Transformers in Time Series Forecasting with Sharpness-Aware Minimization and Channel-Wise Attention

Deep Regression Representation Learning with Topology

Polynomial-based Self-Attention for Table Representation Learning

The Linear Representation Hypothesis and the Geometry of Large Language Models

Feasibility Consistent Representation Learning for Safe Reinforcement Learning

Active Preference Learning for Large Language Models

Merging Multi-Task Models via Weight-Ensembling Mixture of Experts

Video-of-Thought: Step-by-Step Video Reasoning from Perception to Cognition

Matrix Information Theory for Self-Supervised Learning

Data-Efficient Molecular Generation with Hierarchical Textual Inversion

RoSA: Accurate Parameter-Efficient Fine-Tuning via Robust Adaptation

Learning to Compile Programs to Neural Networks

Not all distributional shifts are equal: Fine-grained robust conformal inference

FedRC: Tackling Diverse Distribution Shifts Challenge in Federated Learning by Robust Clustering

Prompt Sketching for Large Language Models

Connect Later: Improving Fine-tuning for Robustness with Targeted Augmentations

Improved Stability and Generalization Guarantees of the Decentralized SGD Algorithm

Adaptive Observation Cost Control for Variational Quantum Eigensolvers

Weakly-Supervised Residual Evidential Learning for Multi-Instance Uncertainty Estimation

(ends 4:00 AM)

3:30 a.m.

Break:

Hosted Lunch

(ends 5:00 AM)

4:30 a.m.

Poster Session 2 [4:30-6:00]

Posters 4:30-6:00

Federated Self-Explaining GNNs with Anti-shortcut Augmentations

Symbolic Music Generation with Non-Differentiable Rule Guided Diffusion

Better Locally Private Sparse Estimation Given Multiple Samples Per User

Automated Statistical Model Discovery with Language Models

Human Alignment of Large Language Models through Online Preference Optimisation

Autoencoding Conditional Neural Processes for Representation Learning

Accelerated Policy Gradient: On the Convergence Rates of the Nesterov Momentum for Reinforcement Learning

Rethinking Generative Large Language Model Evaluation for Semantic Comprehension

Learning and Forgetting Unsafe Examples in Large Language Models

Understanding the Effects of Iterative Prompting on Truthfulness

Robust Multi-Task Learning with Excess Risks

ReLU Network with Width $d+\mathcal{O}(1)$ Can Achieve Optimal Approximation Rate

LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens

Efficient Mixture Learning in Black-Box Variational Inference

Attribute Based Interpretable Evaluation Metrics for Generative Models

Mapping the Multiverse of Latent Representations

Multi-View Clustering by Inter-cluster Connectivity Guided Reward

Case-Based or Rule-Based: How Do Transformers Do the Math?

Analysis for Abductive Learning and Neural-Symbolic Reasoning Shortcuts

Unmasking Vulnerabilities: Cardinality Sketches under Adaptive Inputs

Neuroexplicit Diffusion Models for Inpainting of Optical Flow Fields

Efficient Exploration for LLMs

Density-Softmax: Efficient Test-time Model for Uncertainty Estimation and Robustness under Distribution Shifts

Probabilistic Constrained Reinforcement Learning with Formal Interpretability

Can Mamba Learn How To Learn? A Comparative Study on In-Context Learning Tasks

Automating the Selection of Proxy Variables of Unmeasured Confounders

Conformalized Survival Distributions: A Generic Post-Process to Increase Calibration

Provable Interactive Learning with Hindsight Instruction Feedback

Calibration Bottleneck: Over-compressed Representations are Less Calibratable

Graph Mixup on Approximate Gromov–Wasserstein Geodesics

Geometry-Calibrated DRO: Combating Over-Pessimism with Free Energy Implications

Revisiting Inexact Fixed-Point Iterations for Min-Max Problems: Stochasticity and Structured Nonconvexity

One-Shot Strategic Classification Under Unknown Costs

Fundamental Limits of Distributed Covariance Matrix Estimation Under Communication Constraints

Learning from Memory: Non-Parametric Memory Augmented Self-Supervised Learning of Visual Features

HexGen: Generative Inference of Large Language Model over Heterogeneous Environment

Parameter-Dependent Competitive Analysis for Online Capacitated Coverage Maximization through Boostings and Attenuations

Finding NEM-U: Explaining unsupervised representation learning through neural network generated explanation masks

Position: Amazing Things Come From Having Many Good Models

FreeBind: Free Lunch in Unified Multimodal Space via Knowledge Fusion

Sparsest Models Elude Pruning: An Exposé of Pruning’s Current Capabilities

StableSSM: Alleviating the Curse of Memory in State-space Models through Stable Reparameterization

Prompting4Debugging: Red-Teaming Text-to-Image Diffusion Models by Finding Problematic Prompts

Amortizing Pragmatic Program Synthesis with Rankings

On Stronger Computational Separations Between Multimodal and Unimodal Machine Learning

A New Theoretical Perspective on Data Heterogeneity in Federated Optimization

Break the Sequential Dependency of LLM Inference Using Lookahead Decoding

Position: Towards Unified Alignment Between Agents, Humans, and Environment

TinyTrain: Resource-Aware Task-Adaptive Sparse Training of DNNs at the Data-Scarce Edge

Robust Data-driven Prescriptiveness Optimization

DoraemonGPT: Toward Understanding Dynamic Scenes with Large Language Models (Exemplified as A Video Agent)

Quantum Algorithms and Lower Bounds for Finite-Sum Optimization

Discovering Multiple Solutions from a Single Task in Offline Reinforcement Learning

Batch Singular Value Polarization and Weighted Semantic Augmentation for Universal Domain Adaptation

Learning to Route Among Specialized Experts for Zero-Shot Generalization

LASER: Linear Compression in Wireless Distributed Optimization

Position: Foundation Agents as the Paradigm Shift for Decision Making

Position: Video as the New Language for Real-World Decision Making

DsDm: Model-Aware Dataset Selection with Datamodels

Revisiting Context Aggregation for Image Matting

Improving Neural Additive Models with Bayesian Principles

Learning to Explore for Stochastic Gradient MCMC

PIVOT: Iterative Visual Prompting Elicits Actionable Knowledge for VLMs

Constrained Reinforcement Learning Under Model Mismatch

ULTRAFEEDBACK: Boosting Language Models with Scaled AI Feedback

Studying K-FAC Heuristics by Viewing Adam through a Second-Order Lens

Improving Computational Complexity in Statistical Models with Local Curvature Information

Learning with Adaptive Resource Allocation

Transformers Get Stable: An End-to-End Signal Propagation Theory for Language Models

Statistical Test for Attention Maps in Vision Transformers

A Rate-Distortion View of Uncertainty Quantification

On the Origins of Linear Representations in Large Language Models

Gambling-Based Confidence Sequences for Bounded Random Vectors

DiffDA: a Diffusion model for weather-scale Data Assimilation

Optimistic Multi-Agent Policy Gradient

When and How Does In-Distribution Label Help Out-of-Distribution Detection?

Compressing Large Language Models by Joint Sparsification and Quantization

KernelSHAP-IQ: Weighted Least Square Optimization for Shapley Interactions

Online Matrix Completion: A Collaborative Approach with Hott Items

Two-timescale Derivative Free Optimization for Performative Prediction with Markovian Data

Provably Efficient Long-Horizon Exploration in Monte Carlo Tree Search through State Occupancy Regularization

Decomposing and Editing Predictions by Modeling Model Computation

Position: The No Free Lunch Theorem, Kolmogorov Complexity, and the Role of Inductive Biases in Machine Learning

Kernel Semi-Implicit Variational Inference

Private Truly-Everlasting Robust-Prediction

Fast, Scalable, Warm-Start Semidefinite Programming with Spectral Bundling and Sketching

Outlier-Efficient Hopfield Layers for Large Transformer-Based Models

Maestro: Uncovering Low-Rank Structures via Trainable Decomposition

Regularized Q-learning through Robust Averaging

On Statistical Learning Theory for Distributional Inputs

Beyond the Federation: Topology-aware Federated Learning for Generalization to Unseen Clients

Hybrid Reinforcement Learning from Offline Observation Alone

Test-Time Degradation Adaptation for Open-Set Image Restoration

How Deep Do We Need: Accelerating Training and Inference of Neural ODEs via Control Perspective

SPP: Sparsity-Preserved Parameter-Efficient Fine-Tuning for Large Language Models

Minimax Optimality of Score-based Diffusion Models: Beyond the Density Lower Bound Assumptions

BetterV: Controlled Verilog Generation with Discriminative Guidance

PASOA- PArticle baSed Bayesian Optimal Adaptive design

Optimal Kernel Choice for Score Function-based Causal Discovery

Neural Collapse in Multi-label Learning with Pick-all-label Loss

StableMask: Refining Causal Masking in Decoder-only Transformer

Robustness of Deep Learning for Accelerated MRI: Benefits of Diverse Training Data

Faster Adaptive Decentralized Learning Algorithms

Conditionally-Conjugate Gaussian Process Factor Analysis for Spike Count Data via Data Augmentation

A Doubly Recursive Stochastic Compositional Gradient Descent Method for Federated Multi-Level Compositional Optimization

Surprisingly Strong Performance Prediction with Neural Graph Features

Provable Multi-Task Representation Learning by Two-Layer ReLU Neural Networks

Causal Representation Learning from Multiple Distributions: A General Setting

Reducing Item Discrepancy via Differentially Private Robust Embedding Alignment for Privacy-Preserving Cross Domain Recommendation

Fast White-Box Adversarial Streaming Without a Random Oracle

Envisioning Outlier Exposure by Large Language Models for Out-of-Distribution Detection

Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Models

From Biased Selective Labels to Pseudo-Labels: An Expectation-Maximization Framework for Learning from Biased Decisions

Reducing Fine-Tuning Memory Overhead by Approximate and Memory-Sharing Backpropagation

Neural Tangent Kernels Motivate Cross-Covariance Graphs in Neural Networks

DMTG: One-Shot Differentiable Multi-Task Grouping

Generative Conditional Distributions by Neural (Entropic) Optimal Transport

WISER: Weak Supervision and Supervised Representation Learning to Improve Drug Response Prediction in Cancer

An Efficient Maximal Ancestral Graph Listing Algorithm

Transformers Learn Nonlinear Features In Context: Nonconvex Mean-field Dynamics on the Attention Landscape

Tell, Don't Show: Language Guidance Eases Transfer Across Domains in Images and Videos

Imitation Learning in Discounted Linear MDPs without exploration assumptions

Momentum Particle Maximum Likelihood

Fundamental Limitations of Alignment in Large Language Models

Do Large Code Models Understand Programming Concepts? Counterfactual Analysis for Code Predicates

Offline Inverse RL: New Solution Concepts and Provably Efficient Algorithms

Towards Modular LLMs by Building and Reusing a Library of LoRAs

Codebook Features: Sparse and Discrete Interpretability for Neural Networks

A Linear Time and Space Local Point Cloud Geometry Encoder via Vectorized Kernel Mixture (VecKM)

An Empirical Examination of Balancing Strategy for Counterfactual Estimation on Time Series

Open-Domain Text Evaluation via Contrastive Distribution Methods

A Universal Class of Sharpness-Aware Minimization Algorithms

Transitional Uncertainty with Layered Intermediate Predictions

Scaling Laws for the Value of Individual Data Points in Machine Learning

Controllable Prompt Tuning For Balancing Group Distributional Robustness

Graph-Triggered Rising Bandits

AegisFL: Efficient and Flexible Privacy-Preserving Byzantine-Robust Cross-silo Federated Learning

Graph-enhanced Large Language Models in Asynchronous Plan Reasoning

Position: Standardization of Behavioral Use Clauses is Necessary for the Adoption of Responsible Licensing of AI

Mitigating Catastrophic Forgetting in Online Continual Learning by Modeling Previous Task Interrelations via Pareto Optimization

ReMax: A Simple, Effective, and Efficient Reinforcement Learning Method for Aligning Large Language Models

Convergence and Trade-Offs in Riemannian Gradient Descent and Riemannian Proximal Point

Premier-TACO is a Few-Shot Policy Learner: Pretraining Multitask Representation via Temporal Action-Driven Contrastive Loss

An Image is Worth Multiple Words: Discovering Object Level Concepts using Multi-Concept Prompt Learning

Benign Overfitting in Adversarial Training of Neural Networks

Full-Atom Peptide Design based on Multi-modal Flow Matching

When Will Gradient Regularization Be Harmful?

Rejuvenating image-GPT as Strong Visual Representation Learners

TimeSiam: A Pre-Training Framework for Siamese Time-Series Modeling

MGit: A Model Versioning and Management System

The Effect of Weight Precision on the Neuron Count in Deep ReLU Networks

BayOTIDE: Bayesian Online Multivariate Time Series Imputation with Functional Decomposition

Weakly Convex Regularisers for Inverse Problems: Convergence of Critical Points and Primal-Dual Optimisation

Stochastic positional embeddings improve masked image modeling

Mean-field Analysis on Two-layer Neural Networks from a Kernel Perspective

Byzantine-Robust Federated Learning: Impact of Client Subsampling and Local Updates

Class-Imbalanced Graph Learning without Class Rebalancing

Identification and Estimation for Nonignorable Missing Data: A Data Fusion Approach

R2E: Turning any Github Repository into a Programming Agent Environment

Toward Adaptive Reasoning in Large Language Models with Thought Rollback

Gradient Compressed Sensing: A Query-Efficient Gradient Estimator for High-Dimensional Zeroth-Order Optimization

Stacking Deep Set Networks and Pooling by Quantiles

Straight-Through Meets Sparse Recovery: the Support Exploration Algorithm

Premise Order Matters in Reasoning with Large Language Models

Getting the most out of your tokenizer for pre-training and domain adaptation

VinT-6D: A Large-Scale Object-in-hand Dataset from Vision, Touch and Proprioception

Towards a Better Theoretical Understanding of Independent Subnetwork Training

Perfect Alignment May be Poisonous to Graph Contrastive Learning

Efficient Pareto Manifold Learning with Low-Rank Structure

Generalization Bound and New Algorithm for Clean-Label Backdoor Attack

Federated Representation Learning in the Under-Parameterized Regime

Deep Demonstration Tracing: Learning Generalizable Imitator Policy for Runtime Imitation from a Single Demonstration

Token-Specific Watermarking with Enhanced Detectability and Semantic Coherence for Large Language Models

Incorporating probabilistic domain knowledge into deep multiple instance learning

Robust Optimization in Protein Fitness Landscapes Using Reinforcement Learning in Latent Space

Generalist Equivariant Transformer Towards 3D Molecular Interaction Learning

Enabling Few-Shot Learning with PID Control: A Layer Adaptive Optimizer

An Infinite-Width Analysis on the Jacobian-Regularised Training of a Neural Network

Optimizing Watermarks for Large Language Models

IBD-PSC: Input-level Backdoor Detection via Parameter-oriented Scaling Consistency

SurfPro: Functional Protein Design Based on Continuous Surface

An Empirical Study of Realized GNN Expressiveness

DFA-RAG: Conversational Semantic Router for Large Language Model with Definite Finite Automaton

Fewer Truncations Improve Language Modeling

Improving Prototypical Visual Explanations with Reward Reweighing, Reselection, and Retraining

Forget Sharpness: Perturbed Forgetting of Model Biases Within SAM Dynamics

Position: TrustLLM: Trustworthiness in Large Language Models

Mol-AE: Auto-Encoder Based Molecular Representation Learning With 3D Cloze Test Objective

A Closer Look at the Limitations of Instruction Tuning

Position: Tensor Networks are a Valuable Asset for Green AI

Rolling Diffusion Models

DySLIM: Dynamics Stable Learning by Invariant Measure for Chaotic Systems

Libra: Building Decoupled Vision System on Large Language Models

Collapse-Aware Triplet Decoupling for Adversarially Robust Image Retrieval

Diving into Underwater: Segment Anything Model Guided Underwater Salient Instance Segmentation and A Large-scale Dataset

Revitalizing Multivariate Time Series Forecasting: Learnable Decomposition with Inter-Series Dependencies and Intra-Series Variations Modeling

BeigeMaps: Behavioral Eigenmaps for Reinforcement Learning from Images

Rethinking the Flat Minima Searching in Federated Learning

Self-Supervised Interpretable End-to-End Learning via Latent Functional Modularity

I/O Complexity of Attention, or How Optimal is FlashAttention?

Enhancing Class-Imbalanced Learning with Pre-Trained Guidance through Class-Conditional Knowledge Distillation

ODIN: Disentangled Reward Mitigates Hacking in RLHF

GroupCover: A Secure, Efficient and Scalable Inference Framework for On-device Model Protection based on TEEs

Improving Sharpness-Aware Minimization by Lookahead

Dirichlet Flow Matching with Applications to DNA Sequence Design

Few-Shot Unsupervised Implicit Neural Shape Representation Learning with Spatial Adversaries

Riemannian Preconditioned LoRA for Fine-Tuning Foundation Models

Recurrent Distance Filtering for Graph Representation Learning

Conformal Predictions under Markovian Data

Global Reinforcement Learning : Beyond Linear and Convex Rewards via Submodular Semi-gradient Methods

DistiLLM: Towards Streamlined Distillation for Large Language Models

Expand-and-Cluster: Parameter Recovery of Neural Networks

Fine-Grained Causal Dynamics Learning with Quantization for Improving Robustness in Reinforcement Learning

Overcoming the Optimizer's Curse: Obtaining Realistic Prescriptions from Neural Networks

RigorLLM: Resilient Guardrails for Large Language Models against Undesired Content

A Hierarchical Adaptive Multi-Task Reinforcement Learning Framework for Multiplier Circuit Design

On the Unexpected Effectiveness of Reinforcement Learning for Sequential Recommendation

More Flexible PAC-Bayesian Meta-Learning by Learning Learning Algorithms

Efficient Algorithms for Empirical Group Distributionally Robust Optimization and Beyond

Piecewise Constant and Linear Regression Trees: An Optimal Dynamic Programming Approach

Locally Differentially Private Decentralized Stochastic Bilevel Optimization with Guaranteed Convergence Accuracy

Two-sided Competing Matching Recommendation Markets With Quota and Complementary Preferences Constraints

Position: AI-Powered Autonomous Weapons Risk Geopolitical Instability and Threaten AI Research

Iterative Search Attribution for Deep Neural Networks

Gibbs Sampling of Continuous Potentials on a Quantum Computer

Mechanistic Design and Scaling of Hybrid Architectures

Diversified Batch Selection for Training Acceleration

SimPro: A Simple Probabilistic Framework Towards Realistic Long-Tailed Semi-Supervised Learning

Sample Complexity Bounds for Estimating Probability Divergences under Invariances

Zero-Sum Positional Differential Games as a Framework for Robust Reinforcement Learning: Deep Q-Learning Approach

Topological Neural Networks go Persistent, Equivariant, and Continuous

Sharpness-Aware Data Generation for Zero-shot Quantization

Block Acceleration Without Momentum: On Optimal Stepsizes of Block Gradient Descent for Least-Squares

DPZero: Private Fine-Tuning of Language Models without Backpropagation

Bayesian Regret Minimization in Offline Bandits

A Near-Linear Time Approximation Algorithm for Beyond-Worst-Case Graph Clustering

Listenable Maps for Audio Classifiers

A Field Guide for Pacing Budget and ROS Constraints

Improving Transformers with Dynamically Composable Multi-Head Attention

Generating Chain-of-Thoughts with a Pairwise-Comparison Approach to Searching for the Most Promising Intermediate Thought

Representation Surgery for Multi-Task Model Merging

How Do Nonlinear Transformers Learn and Generalize in In-Context Learning?

AD3: Implicit Action is the Key for World Models to Distinguish the Diverse Visual Distractors

Any-Precision LLM: Low-Cost Deployment of Multiple, Different-Sized LLMs

On the Recoverability of Causal Relations from Temporally Aggregated I.I.D. Data

Visual Representation Learning with Stochastic Frame Prediction

Efficient Low-Rank Matrix Estimation, Experimental Design, and Arm-Set-Dependent Low-Rank Bandits

What is Dataset Distillation Learning?

Language Agents with Reinforcement Learning for Strategic Play in the Werewolf Game

On the Universality of Volume-Preserving and Coupling-Based Normalizing Flows

Aligned Objective for Soft-Pseudo-Label Generation in Supervised Learning

SiBBlInGS: Similarity-driven Building-Block Inference using Graphs across States

SyCoCa: Symmetrizing Contrastive Captioners with Attentive Masking for Multimodal Alignment

WorkArena: How Capable are Web Agents at Solving Common Knowledge Work Tasks?

Discovering Bias in Latent Space: An Unsupervised Debiasing Approach

The Entropy Enigma: Success and Failure of Entropy Minimization

AttnLRP: Attention-Aware Layer-Wise Relevance Propagation for Transformers

Vision Transformers as Probabilistic Expansion from Learngene

High-Dimensional Bayesian Optimization via Semi-Supervised Learning with Optimized Unlabeled Data Sampling

A Differentiable Partially Observable Generalized Linear Model with Forward-Backward Message Passing

Bringing Motion Taxonomies to Continuous Domains via GPLVM on Hyperbolic manifolds

Probabilistic Routing for Graph-Based Approximate Nearest Neighbor Search

SF-DQN: Provable Knowledge Transfer using Successor Feature for Deep Reinforcement Learning

Watermarks in the Sand: Impossibility of Strong Watermarking for Language Models

Neural SPH: Improved Neural Modeling of Lagrangian Fluid Dynamics

Sub-token ViT Embedding via Stochastic Resonance Transformers

Transformers Implement Functional Gradient Descent to Learn Non-Linear Functions In Context

Turnstile $\ell_p$ leverage score sampling with applications

MILP-FBGen: LP/MILP Instance Generation with Feasibility/Boundedness

Sarah Frank-Wolfe: Methods for Constrained Optimization with Best Rates and Practical Features

Hierarchical Novelty Detection via Fine-Grained Evidence Allocation

Decentralized Convex Finite-Sum Optimization with Better Dependence on Condition Numbers

Unsupervised Zero-Shot Reinforcement Learning via Functional Reward Encodings

Less is More: on the Over-Globalizing Problem in Graph Transformers

Refining Minimax Regret for Unsupervised Environment Design

A Fixed-Point Approach for Causal Generative Modeling

Weisfeiler Leman for Euclidean Equivariant Machine Learning

Multiply-Robust Causal Change Attribution

HumanTOMATO: Text-aligned Whole-body Motion Generation

Diffusion Posterior Sampling is Computationally Intractable

Diffusion Model-Augmented Behavioral Cloning

EvoluNet: Advancing Dynamic Non-IID Transfer Learning on Graphs

RIME: Robust Preference-based Reinforcement Learning with Noisy Preferences

Two-Stage Shadow Inclusion Estimation: An IV Approach for Causal Inference under Latent Confounding and Collider Bias

Magicoder: Empowering Code Generation with OSS-Instruct

Listwise Reward Estimation for Offline Preference-based Reinforcement Learning

Time-Series Forecasting for Out-of-Distribution Generalization Using Invariant Learning

Generalization Analysis of Deep Non-linear Matrix Completion

DITTO: Diffusion Inference-Time T-Optimization for Music Generation

LayerMerge: Neural Network Depth Compression through Layer Pruning and Merging

GLoRe: When, Where, and How to Improve LLM Reasoning via Global and Local Refinements

Minimally Modifying a Markov Game to Achieve Any Nash Equilibrium and Value

A sampling theory perspective on activations for implicit neural representations

Accelerating Convergence in Bayesian Few-Shot Classification

PPFLOW: Target-Aware Peptide Design with Torsional Flow Matching

Pessimism Meets Risk: Risk-Sensitive Offline Reinforcement Learning

In-Context Learning Agents Are Asymmetric Belief Updaters

Improved Differentially Private and Lazy Online Convex Optimization: Lower Regret without Smoothness Requirements

Socialized Learning: Making Each Other Better Through Multi-Agent Collaboration

Improved Modelling of Federated Datasets using Mixtures-of-Dirichlet-Multinomials

Gaussian Processes on Cellular Complexes

Masked Face Recognition with Generative-to-Discriminative Representations

Learning Exceptional Subgroups by End-to-End Maximizing KL-Divergence

Characterizing Truthfulness in Large Language Model Generations with Local Intrinsic Dimension

Adapting Pretrained ViTs with Convolution Injector for Visuo-Motor Control

Adaptive Conformal Inference by Betting

Momentor: Advancing Video Large Language Model with Fine-Grained Temporal Reasoning

Scaling Exponents Across Parameterizations and Optimizers

LIDAO: Towards Limited Interventions for Debiasing (Large) Language Models

A New Robust Partial p-Wasserstein-Based Metric for Comparing Distributions

Position: Technical Research and Talent is Needed for Effective AI Governance

Sign Rank Limitations for Inner Product Graph Decoders

CaRiNG: Learning Temporal Causal Representation under Non-Invertible Generation Process

On PI Controllers for Updating Lagrange Multipliers in Constrained Optimization

Prospective Side Information for Latent MDPs

convSeq: Fast and Scalable Method for Detecting Patterns in Spike Data

DiJiang: Efficient Large Language Models through Compact Kernelization

STEER: Assessing the Economic Rationality of Large Language Models

On the Generalization of Stochastic Gradient Descent with Momentum

Simulation-Based Inference with Quantile Regression

Selecting Large Language Model to Fine-tune via Rectified Scaling Law

On the Second-Order Convergence of Biased Policy Gradient Algorithms

Exploring Training on Heterogeneous Data with Mixture of Low-rank Adapters

Compositional Text-to-Image Generation with Dense Blob Representations

Stationary Latent Weight Inference for Unreliable Observations from Online Test-Time Adaptation

Fast Sampling-Based Sketches for Tensors

Embodied CoT Distillation From LLM To Off-the-shelf Agents

Debiased Distribution Compression

Improved Generalization of Weight Space Networks via Augmentations

Dynamic Evaluation of Large Language Models by Meta Probing Agents

The Non-linear $F$-Design and Applications to Interactive Learning

Coresets for Multiple $\ell_p$ Regression

Guarantees for Nonlinear Representation Learning: Non-identical Covariates, Dependent Data, Fewer Samples

Variational Partial Group Convolutions for Input-Aware Partial Equivariance of Rotations and Color-Shifts

PrE-Text: Training Language Models on Private Federated Data in the Age of LLMs

State-Constrained Zero-Sum Differential Games with One-Sided Information

Learning Constraints from Offline Demonstrations via Superior Distribution Correction Estimation

Non-convex Stochastic Composite Optimization with Polyak Momentum

Referee Can Play: An Alternative Approach to Conditional Generation via Model Inversion

Slicing Mutual Information Generalization Bounds for Neural Networks

Improving Robustness to Multiple Spurious Correlations by Multi-Objective Optimization

Acquisition Conditioned Oracle for Nongreedy Active Feature Acquisition

Optimal Recurrent Network Topologies for Dynamical Systems Reconstruction

Concentration Inequalities for General Functions of Heavy-Tailed Random Variables

Position: On the Societal Impact of Open Foundation Models

Multi-class Probabilistic Bounds for Majority Vote Classifiers with Partially Labeled Data

Constrained Ensemble Exploration for Unsupervised Skill Discovery

Learning with Complementary Labels Revisited: The Selected-Completely-at-Random Setting Is More Practical

Fast Timing-Conditioned Latent Audio Diffusion

DAG-Based Column Generation for Adversarial Team Games

Impact of Decentralized Learning on Player Utilities in Stackelberg Games

Rapid Learning without Catastrophic Forgetting in the Morris Water Maze

Position: LLMs Can’t Plan, But Can Help Planning in LLM-Modulo Frameworks

Ranking-based Client Imitation Selection for Efficient Federated Learning

Selective Mixup Helps with Distribution Shifts, But Not (Only) because of Mixup

Multi-Patch Prediction: Adapting Language Models for Time Series Representation Learning

From Vision to Audio and Beyond: A Unified Model for Audio-Visual Representation and Generation

Robust Graph Matching when Nodes are Corrupt

Explaining Probabilistic Models with Distributional Values

Adaptive Text Watermark for Large Language Models

Navigating Scaling Laws: Compute Optimality in Adaptive Model Training

Trustworthy Alignment of Retrieval-Augmented Large Language Models via Reinforcement Learning

ReGAL: Refactoring Programs to Discover Generalizable Abstractions

Position: Building Guardrails for Large Language Models Requires Systematic Design

Position: Why Tabular Foundation Models Should Be a Research Priority

Augmenting Decision with Hypothesis in Reinforcement Learning

ViP: A Differentially Private Foundation Model for Computer Vision

Learning-Efficient Yet Generalizable Collaborative Filtering for Item Recommendation

How Universal Polynomial Bases Enhance Spectral Graph Neural Networks: Heterophily, Over-smoothing, and Over-squashing

Improved Operator Learning by Orthogonal Attention

Privacy-Preserving Embedding via Look-up Table Evaluation with Fully Homomorphic Encryption

Learning Iterative Reasoning through Energy Diffusion

Deep Networks Always Grok and Here is Why

Towards Understanding the Word Sensitivity of Attention Layers: A Study via Random Features

Partial Optimality in the Linear Ordering Problem

Cross-Domain Policy Adaptation by Capturing Representation Mismatch

Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models

STELLA: Continual Audio-Video Pre-training with SpatioTemporal Localized Alignment

Bounded and Uniform Energy-based Out-of-distribution Detection for Graphs

Compositional Curvature Bounds for Deep Neural Networks

How Private are DP-SGD Implementations?

Improving Token-Based World Models with Parallel Observation Prediction

Prodigy: An Expeditiously Adaptive Parameter-Free Learner

Scaling Speech Technology to 1,000+ Languages

Online Resource Allocation with Non-Stationary Customers

Lightweight Image Super-Resolution via Flexible Meta Pruning

Robustness of Nonlinear Representation Learning

Non-stationary Online Convex Optimization with Arbitrary Delays

Recovering the Pre-Fine-Tuning Weights of Generative Models

Slot Abstractors: Toward Scalable Abstract Visual Reasoning

Efficient Error Certification for Physics-Informed Neural Networks

Optimal Ridge Regularization for Out-of-Distribution Prediction

Conformal Prediction for Deep Classifier via Label Ranking

Collaborative Learning with Different Labeling Functions

DecisionNCE: Embodied Multimodal Representations via Implicit Preference Learning

Trustless Audits without Revealing Data or Models

An Online Optimization Perspective on First-Order and Zero-Order Decentralized Nonsmooth Nonconvex Stochastic Optimization

Position: Topological Deep Learning is the New Frontier for Relational Learning

Symmetry Induces Structure and Constraint of Learning

FlowMM: Generating Materials with Riemannian Flow Matching

Diffusion Models Demand Contrastive Guidance for Adversarial Purification to Advance

PIDformer: Transformer Meets Control Theory

Loss Shaping Constraints for Long-Term Time Series Forecasting

LLM Maybe LongLM: SelfExtend LLM Context Window Without Tuning

Solving Hierarchical Information-Sharing Dec-POMDPs: An Extensive-Form Game Approach

Position: Understanding LLMs Requires More Than Statistical Generalization

Position: Data Authenticity, Consent, & Provenance for AI are all broken: what will it take to fix them?

Learning Label Shift Correction for Test-Agnostic Long-Tailed Recognition

Contamination-Resilient Anomaly Detection via Adversarial Learning on Partially-Observed Normal and Anomalous Data

Optimization without Retraction on the Random Generalized Stiefel Manifold

Trust Regions for Explanations via Black-Box Probabilistic Certification

Position: A Call for Embodied AI

LangCell: Language-Cell Pre-training for Cell Identity Understanding

Continuous Treatment Effects with Surrogate Outcomes

Stealthy Imitation: Reward-guided Environment-free Policy Stealing

Position: The Platonic Representation Hypothesis

Weighted distance nearest neighbor condensing

Learning Optimal Deterministic Policies with Stochastic Policy Gradients

DSD-DA: Distillation-based Source Debiasing for Domain Adaptive Object Detection

On the Effectiveness of Supervision in Asymmetric Non-Contrastive Learning

Creative Text-to-Audio Generation via Synthesizer Programming

Pi-DUAL: Using privileged information to distinguish clean from noisy labels

Scalable Real-Time Recurrent Learning Using Columnar-Constructive Networks

Rethinking Momentum Knowledge Distillation in Online Continual Learning

MAGNOLIA: Matching Algorithms via GNNs for Online Value-to-go Approximation

DS-Agent: Automated Data Science by Empowering Large Language Models with Case-Based Reasoning

Let Go of Your Labels with Unsupervised Transfer

InterLUDE: Interactions between Labeled and Unlabeled Data to Enhance Semi-Supervised Learning

Position: Cracking the Code of Cascading Disparity Towards Marginalized Communities

Fast-Slow Test-Time Adaptation for Online Vision-and-Language Navigation

Stochastic Q-learning for Large Discrete Action Spaces

How to Escape Sharp Minima with Random Perturbations

Matroid Semi-Bandits in Sublinear Time

APT: Adaptive Pruning and Tuning Pretrained Language Models for Efficient Training and Inference

Inverse-Variance Weighting for Estimation of Heterogeneous Treatment Effects

Physics of Language Models: Part 3.1, Knowledge Storage and Extraction

Characteristic Guidance: Non-linear Correction for Diffusion Model at Large Guidance Scale

Offline Imitation from Observation via Primal Wasserstein State Occupancy Matching

GNNs Also Deserve Editing, and They Need It More Than Once

SelfIE: Self-Interpretation of Large Language Model Embeddings

Triple Changes Estimator for Targeted Policies

AND: Audio Network Dissection for Interpreting Deep Acoustic Models

Enhancing Adversarial Robustness in SNNs with Sparse Gradients

Compressible Dynamics in Deep Overparameterized Low-Rank Learning & Adaptation

(ends 6:00 AM)

6 a.m.

Invited Talk:

The effects of digital technology on youth development in low-and-middle-income countries

Lucía Magis-Weinberg

(ends 7:00 AM)

7 a.m.

Break:

Coffee Break

(ends 7:30 AM)

7:30 a.m.

Oral 2x Positions on AI Opportunities and Risks for Society [7:30-8:30]

Orals 7:30-8:30

[7:30] Position: Technical Research and Talent is Needed for Effective AI Governance

[7:45] Position: AI-Powered Autonomous Weapons Risk Geopolitical Instability and Threaten AI Research

[8:00] Position: Near to Mid-term Risks and Opportunities of Open-Source Generative AI

[8:15] Position: On the Societal Impact of Open Foundation Models

(ends 8:30 AM)

Oral 2x Privacy [7:30-8:30]

Orals 7:30-8:30

[7:30] How Private are DP-SGD Implementations?

[7:45] Private Truly-Everlasting Robust-Prediction

[8:00] ViP: A Differentially Private Foundation Model for Computer Vision

[8:15] PrE-Text: Training Language Models on Private Federated Data in the Age of LLMs

(ends 8:30 AM)

Oral 2x Efficient LLMs [7:30-8:30]

Orals 7:30-8:30

[7:30] Compressible Dynamics in Deep Overparameterized Low-Rank Learning & Adaptation

[7:45] APT: Adaptive Pruning and Tuning Pretrained Language Models for Efficient Training and Inference

[8:00] DiJiang: Efficient Large Language Models through Compact Kernelization

[8:15] Any-Precision LLM: Low-Cost Deployment of Multiple, Different-Sized LLMs

(ends 8:30 AM)

Oral 2x Music and audio [7:30-8:30]

Orals 7:30-8:30

[7:30] Symbolic Music Generation with Non-Differentiable Rule Guided Diffusion

[7:45] DITTO: Diffusion Inference-Time T-Optimization for Music Generation

[8:00] Fast Timing-Conditioned Latent Audio Diffusion

[8:15] Listenable Maps for Audio Classifiers

(ends 8:30 AM)

Oral 2x Representation Learning 1 [7:30-8:30]

Orals 7:30-8:30

[7:30] Position: The Platonic Representation Hypothesis

[7:45] Robustness of Nonlinear Representation Learning

[8:00] Provable Multi-Task Representation Learning by Two-Layer ReLU Neural Networks

[8:15] Rejuvenating image-GPT as Strong Visual Representation Learners

(ends 8:30 AM)

Oral 2x Attention [7:30-8:30]

Orals 7:30-8:30

[7:30] Transformers Learn Nonlinear Features In Context: Nonconvex Mean-field Dynamics on the Attention Landscape

[7:45] I/O Complexity of Attention, or How Optimal is FlashAttention?

[8:00] Improving Transformers with Dynamically Composable Multi-Head Attention

[8:15] Less is More: on the Over-Globalizing Problem in Graph Transformers

(ends 8:30 AM)

11:30 p.m.

Registration

(ends 9:00 AM)

WED 24 JUL

midnight

Workshop:

Women in Machine Learning (WiML) Affinity Workshop Proposal for ICML 2024

(ends 7:00 AM)

Invited Talk:

Vukosi Marivate

(ends 1:00 AM)

1 a.m.

Break:

Coffee Break

(ends 1:30 AM)

1:30 a.m.

Oral 3x Diffusion Models [1:30-2:30]

Orals 1:30-2:30

[1:30] Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution

[1:45] Mean-field Chaos Diffusion Models

[2:00] NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Models

[2:15] Scaling Rectified Flow Transformers for High-Resolution Image Synthesis

(ends 2:30 AM)

Oral 3x LLMs: Code and Arithmetic [1:30-2:30]

Orals 1:30-2:30

[1:30] Chain of Code: Reasoning with a Language Model-Augmented Code Emulator

[1:45] SceneCraft: An LLM Agent for Synthesizing 3D Scenes as Blender Code

[2:00] Interpreting and Improving Large Language Models in Arithmetic Calculation

[2:15] Evaluation of LLMs on Syntax-Aware Code Fill-in-the-Middle Tasks

(ends 2:30 AM)

Oral 3x Probabilistic Inference [1:30-2:30]

Orals 1:30-2:30

[1:30] Active Statistical Inference

[1:45] Sparse Inducing Points in Deep Gaussian Processes: Enhancing Modeling with Denoising Diffusion Variational Inference

[2:00] Probabilistic Generating Circuits - Demystified

[2:15] Probabilistic Inference in Language Models via Twisted Sequential Monte Carlo

(ends 2:30 AM)

Oral 3x Causality [1:30-2:30]

Orals 1:30-2:30

[1:30] Doubly Robust Causal Effect Estimation under Networked Interference via Targeted Learning

[1:45] Hybrid$^2$ Neural ODE Causal Modeling and an Application to Glycemic Response

[2:00] Inferring the Long-Term Causal Effects of Long-Term Treatments from Short-Term Experiments

[2:15] ACE: Off-Policy Actor-Critic with Causality-Aware Entropy Regularization

(ends 2:30 AM)

Oral 3x Data and Society [1:30-2:30]

Orals 1:30-2:30

[1:30] Position: Measure Dataset Diversity, Don't Just Claim It

[1:45] Rethinking Data Shapley for Data Selection Tasks: Misleads and Merits

[2:00] Monitoring AI-Modified Content at Scale: A Case Study on the Impact of ChatGPT on AI Conference Peer Reviews

[2:15] Differentiable Mapper for Topological Optimization of Data Representation

(ends 2:30 AM)

Oral 3x Reinforcement Learning 1 [1:30-2:30]

Orals 1:30-2:30

[1:30] Position: Automatic Environment Shaping is the Next Frontier in RL

[1:45] Pausing Policy Learning in Non-stationary Reinforcement Learning

[2:00] OMPO: A Unified Framework for RL under Policy and Dynamics Shifts

[2:15] Online Matching with Stochastic Rewards: Provable Better Bound via Adversarial Reinforcement Learning

(ends 2:30 AM)

2:30 a.m.

Poster Session 3 [2:30-4:00]

Posters 2:30-4:00

TSLANet: Rethinking Transformers for Time Series Representation Learning

Federated Full-Parameter Tuning of Billion-Sized Language Models with Communication Cost under 18 Kilobytes

Disentanglement Learning via Topology

Predictive Dynamic Fusion

Position: Automatic Environment Shaping is the Next Frontier in RL

Just Cluster It: An Approach for Exploration in High-Dimensions using Clustering and Pre-Trained Representations

Interpreting and Improving Diffusion Models from an Optimization Perspective

Modular Learning of Deep Causal Generative Models for High-dimensional Causal Inference

Cross-view Masked Diffusion Transformers for Person Image Synthesis

Multi-Sender Persuasion: A Computational Perspective

Energy-Efficient Gaussian Processes Using Low-Precision Arithmetic

On dimensionality of feature vectors in MPNNs

Scale-Free Image Keypoints Using Differentiable Persistent Homology

Amortized Variational Deep Kernel Learning

Bidirectional Reciprocative Information Communication for Few-Shot Semantic Segmentation

USTAD: Unified Single-model Training Achieving Diverse Scores for Information Retrieval

Interpreting and Improving Large Language Models in Arithmetic Calculation

TravelPlanner: A Benchmark for Real-World Planning with Language Agents

Unified Generation, Reconstruction, and Representation: Generalized Diffusion with Adaptive Latent Encoding-Decoding

Asymptotically Optimal and Computationally Efficient Average Treatment Effect Estimation in A/B testing

Understanding Reasoning Ability of Language Models From the Perspective of Reasoning Paths Aggregation

In-Context Freeze-Thaw Bayesian Optimization for Hyperparameter Optimization

Revealing Vision-Language Integration in the Brain with Multimodal Networks

Total Variation Floodgate for Variable Importance Inference in Classification

Stay on Topic with Classifier-Free Guidance

SiT: Symmetry-invariant Transformers for Generalisation in Reinforcement Learning

Bagged Deep Image Prior for Recovering Images in the Presence of Speckle Noise

ELF: Encoding Speaker-Specific Latent Speech Feature for Speech Synthesis

Towards Theoretical Understandings of Self-Consuming Generative Models

${\rm E}(3)$-Equivariant Actor-Critic Methods for Cooperative Multi-Agent Reinforcement Learning

TENG: Time-Evolving Natural Gradient for Solving PDEs With Deep Neural Nets Toward Machine Precision

Transport of Algebraic Structure to Latent Embeddings

Combining Experimental and Historical Data for Policy Evaluation

Ditto: Quantization-aware Secure Inference of Transformers upon MPC

Latent Optimal Paths by Gumbel Propagation for Variational Bayesian Dynamic Programming

Conditional Common Entropy for Instrumental Variable Testing and Partial Identification

Stochastic Quantum Sampling for Non-Logconcave Distributions and Estimating Partition Functions

Controlled Decoding from Language Models

Limited Preference Aided Imitation Learning from Imperfect Demonstrations

Probabilistic Inference in Language Models via Twisted Sequential Monte Carlo

Accelerating Legacy Numerical Solvers by Non-intrusive Gradient-based Meta-solving

Prototypical Transformer As Unified Motion Learners

Tilting the Odds at the Lottery: the Interplay of Overparameterisation and Curricula in Neural Networks

ReLU to the Rescue: Improve Your On-Policy Actor-Critic with Positive Advantages

Beyond Sole Strength: Customized Ensembles for Generalized Vision-Language Models

Semantically-correlated memories in a dense associative model

No-Regret Reinforcement Learning in Smooth MDPs

Dynamic Byzantine-Robust Learning: Adapting to Switching Byzantine Workers

Jetfire: Efficient and Accurate Transformer Pretraining with INT8 Data Flow and Per-Block Quantization

The Benefits of Reusing Batches for Gradient Descent in Two-Layer Networks: Breaking the Curse of Information and Leap Exponents

A Neural-Preconditioned Poisson Solver for Mixed Dirichlet and Neumann Boundary Conditions

Learning to Scale Logits for Temperature-Conditional GFlowNets

How Spurious Features are Memorized: Precise Analysis for Random and NTK Features

Learning Causal Dynamics Models in Object-Oriented Environments

Bayesian Optimization of Function Networks with Partial Evaluations

Differentiable Mapper for Topological Optimization of Data Representation

Mean-field Chaos Diffusion Models

A Minimaximalist Approach to Reinforcement Learning from Human Feedback

Differentially Private Domain Adaptation with Theoretical Guarantees

Better & Faster Large Language Models via Multi-token Prediction

Adaptive Group Personalization for Federated Mutual Transfer Learning

StackSight: Unveiling WebAssembly through Large Language Models and Neurosymbolic Chain-of-Thought Decompilation

SuDA: Support-based Domain Adaptation for Sim2Real Hinge Joint Tracking with Flexible Sensors

FairProof : Confidential and Certifiable Fairness for Neural Networks

CauDiTS: Causal Disentangled Domain Adaptation of Multivariate Time Series

Community-Invariant Graph Contrastive Learning

Provably Efficient Exploration in Quantum Reinforcement Learning with Logarithmic Worst-Case Regret

Tabular Insights, Visual Impacts: Transferring Expertise from Tables to Images

Decoupling Feature Extraction and Classification Layers for Calibrated Neural Networks

FADAS: Towards Federated Adaptive Asynchronous Optimization

Attack-free Evaluating and Enhancing Adversarial Robustness on Categorical Data

MMT-Bench: A Comprehensive Multimodal Benchmark for Evaluating Large Vision-Language Models Towards Multitask AGI

More Benefits of Being Distributional: Second-Order Bounds for Reinforcement Learning

Differentially Private Decentralized Learning with Random Walks

Compositional Capabilities of Autoregressive Transformers: A Study on Synthetic, Interpretable Tasks

A Fine-grained Analysis of Fitted Q-evaluation: Beyond Parametric Models

Dynamic Facility Location in High Dimensional Euclidean Spaces

Criterion Collapse and Loss Distribution Control

Purifying Quantization-conditioned Backdoors via Layer-wise Activation Correction with Distribution Approximation

Rethinking Data Shapley for Data Selection Tasks: Misleads and Merits

D-Flow: Differentiating through Flows for Controlled Generation

Predictive Performance Comparison of Decision Policies Under Confounding

Revisiting Scalable Hessian Diagonal Approximations for Applications in Reinforcement Learning

Accelerating Federated Learning with Quick Distributed Mean Estimation

Confronting Reward Overoptimization for Diffusion Models: A Perspective of Inductive and Primacy Biases

Provably Neural Active Learning Succeeds via Prioritizing Perplexing Samples

A Bias-Variance-Covariance Decomposition of Kernel Scores for Generative Models

Random Exploration in Bayesian Optimization: Order-Optimal Regret and Computational Efficiency

DIDI: Diffusion-Guided Diversity for Offline Behavioral Generation

Leveraging (Biased) Information: Multi-armed Bandits with Offline Data

Monitoring AI-Modified Content at Scale: A Case Study on the Impact of ChatGPT on AI Conference Peer Reviews

SMaRt: Improving GANs with Score Matching Regularity

Generative Flows on Discrete State-Spaces: Enabling Multimodal Flows with Applications to Protein Co-Design

SelfVC: Voice Conversion With Iterative Refinement using Self Transformations

Exploring the Low-Pass Filtering Behavior in Image Super-Resolution

Multimodal Prototyping for cancer survival prediction

ACE: Off-Policy Actor-Critic with Causality-Aware Entropy Regularization

Self-Infilling Code Generation

Agent Instructs Large Language Models to be General Zero-Shot Reasoners

Federated Continual Learning via Prompt-based Dual Knowledge Transfer

Exploration by Optimization with Hybrid Regularizers: Logarithmic Regret with Adversarial Robustness in Partial Monitoring

ContPhy: Continuum Physical Concept Learning and Reasoning from Videos

Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution

Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models

Graph Attention Retrospective

Gradient-based Visual Explanation for Transformer-based CLIP

Harmonizing Generalization and Personalization in Federated Prompt Learning

Tag-LLM: Repurposing General-Purpose LLMs for Specialized Domains

Privacy Profiles for Private Selection

PDHG-Unrolled Learning-to-Optimize Method for Large-Scale Linear Programming

What’s the score? Automated Denoising Score Matching for Nonlinear Diffusions

Improving Group Robustness on Spurious Correlation Requires Preciser Group Inference

Local Causal Structure Learning in the Presence of Latent Variables

Towards Understanding Inductive Bias in Transformers: A View From Infinity

Measuring Stochastic Data Complexity with Boltzmann Influence Functions

How Well Can LLMs Negotiate? NegotiationArena Platform and Analysis

Graph Generation with Diffusion Mixture

Faithfulness Measurable Masked Language Models

Towards Efficient Training and Evaluation of Robust Models against $l_0$ Bounded Adversarial Perturbations

Effective Federated Graph Matching

DFlow: A Generative Model Combining Denoising AutoEncoder and Normalizing Flow for High Fidelity Waveform Generation

Multicalibration for Confidence Scoring in LLMs

An Empirical Study Into What Matters for Calibrating Vision-Language Models

Enhancing Value Function Estimation through First-Order State-Action Dynamics in Offline Reinforcement Learning

Estimating Barycenters of Distributions with Neural Optimal Transport

Promoting External and Internal Equities Under Ex-Ante/Ex-Post Metrics in Online Resource Allocation

The Emergence of Reproducibility and Consistency in Diffusion Models

PANDA: Expanded Width-Aware Message Passing Beyond Rewiring

Sparse Cocktail: Every Sparse Pattern Every Sparse Ratio All At Once

Vanilla Bayesian Optimization Performs Great in High Dimensions

Supervised Matrix Factorization: Local Landscape Analysis and Applications

MALIBO: Meta-learning for Likelihood-free Bayesian Optimization

Don't be so Negative! Score-based Generative Modeling with Oracle-assisted Guidance

Chain of Code: Reasoning with a Language Model-Augmented Code Emulator

RoboCodeX: Multimodal Code Generation for Robotic Behavior Synthesis

Prediction Accuracy of Learning in Games : Follow-the-Regularized-Leader meets Heisenberg

Log Neural Controlled Differential Equations: The Lie Brackets Make A Difference

Tandem Transformers for Inference Efficient LLMs

Sequential Neural Score Estimation: Likelihood-Free Inference with Conditional Score Based Diffusion Models

On a Neural Implementation of Brenier's Polar Factorization

Listening to the noise: Blind Denoising with Gibbs Diffusion

Near-Optimal Reinforcement Learning with Self-Play under Adaptivity Constraints

On the Role of Edge Dependency in Graph Generative Models

Learning Universal Predictors

Feasible Reachable Policy Iteration

Network Tight Community Detection

Optimal Coresets for Low-Dimensional Geometric Median

CLIPZyme: Reaction-Conditioned Virtual Screening of Enzymes

Auto-Regressive Next-Token Predictors are Universal Learners

Learning Decision Trees and Forests with Algorithmic Recourse

Zero-Shot ECG Classification with Multimodal Learning and Test-time Clinical Knowledge Enhancement

PinNet: Pinpoint Instructive Information for Retrieval Augmented Code-to-Text Generation

Reflective Policy Optimization

Partially Stochastic Infinitely Deep Bayesian Neural Networks

Position: Explain to Question not to Justify

DPOT: Auto-Regressive Denoising Operator Transformer for Large-Scale PDE Pre-Training

InterpreTabNet: Distilling Predictive Signals from Tabular Data by Salient Feature Interpretation

The good, the bad and the ugly sides of data augmentation: An implicit spectral regularization perspective

Multi-View Stochastic Block Models

Decoding-time Realignment of Language Models

Neural NeRF Compression

Target Networks and Over-parameterization Stabilize Off-policy Bootstrapping with Function Approximation

Riemannian coordinate descent algorithms on matrix manifolds

Bayesian Exploration Networks

Keypoint-based Progressive Chain-of-Thought Distillation for LLMs

MS-TIP: Imputation Aware Pedestrian Trajectory Prediction

LLark: A Multimodal Instruction-Following Language Model for Music

Rich-Observation Reinforcement Learning with Continuous Latent Dynamics

Acquiring Diverse Skills using Curriculum Reinforcement Learning with Mixture of Experts

Balancing Similarity and Complementarity for Federated Learning

Exploring the Enigma of Neural Dynamics Through A Scattering-Transform Mixer Landscape for Riemannian Manifold

Active Statistical Inference

A Generative Approach for Treatment Effect Estimation under Collider Bias: From an Out-of-Distribution Perspective

What Would Gauss Say About Representations? Probing Pretrained Image Models using Synthetic Gaussian Benchmarks

Spectral Phase Transition and Optimal PCA in Block-Structured Spiked Models

Transferable Facial Privacy Protection against Blind Face Restoration via Domain-Consistent Adversarial Obfuscation

Unsupervised Parameter-free Simplicial Representation Learning with Scattering Transforms

NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Models

How Far Can Fairness Constraints Help Recover From Biased Data?

Stability and Generalization of Stochastic Compositional Gradient Descent Algorithms

A Nearly Optimal Single Loop Algorithm for Stochastic Bilevel Optimization under Unbounded Smoothness

PointMC: Multi-instance Point Cloud Registration based on Maximal Cliques

GRATH: Gradual Self-Truthifying for Large Language Models

Amend to Alignment: Decoupled Prompt Tuning for Mitigating Spurious Correlation in Vision-Language Models

ConTextual: Evaluating Context-Sensitive Text-Rich Visual Reasoning in Large Multimodal Models

Offline Multi-Objective Optimization

Distributional Bellman Operators over Mean Embeddings

Self-Correcting Self-Consuming Loops for Generative Model Training

Long Is More for Alignment: A Simple but Tough-to-Beat Baseline for Instruction Fine-Tuning

Language Models as Science Tutors

Information-Directed Pessimism for Offline Reinforcement Learning

Recurrent Early Exits for Federated Learning with Heterogeneous Clients

Offline Transition Modeling via Contrastive Energy Learning

Position: What makes an image realistic?

Multi-Agent Reinforcement Learning Meets Leaf Sequencing in Radiotherapy

Sparse Model Inversion: Efficient Inversion of Vision Transformers for Data-Free Applications

Online Isolation Forest

Pausing Policy Learning in Non-stationary Reinforcement Learning

How Learning by Reconstruction Produces Uninformative Features For Perception

RVI-SAC: Average Reward Off-Policy Deep Reinforcement Learning

Improving Factuality and Reasoning in Language Models through Multiagent Debate

The Relative Value of Prediction in Algorithmic Decision Making

Simultaneous identification of models and parameters of scientific simulators

A General Online Algorithm for Optimizing Complex Performance Metrics

One Meta-tuned Transformer is What You Need for Few-shot Learning

Visual Transformer with Differentiable Channel Selection: An Information Bottleneck Inspired Approach

Fine-grained Classes and How to Find Them

SleepFM: Multi-modal Representation Learning for Sleep Across Brain Activity, ECG and Respiratory Signals

Breadth-First Exploration on Adaptive Grid for Reinforcement Learning

BBox-Adapter: Lightweight Adapting for Black-Box Large Language Models

Completing Visual Objects via Bridging Generation and Segmentation

FAFE: Immune Complex Modeling with Geodesic Distance Loss on Noisy Group Frames

Borda Regret Minimization for Generalized Linear Dueling Bandits

Hybrid$^2$ Neural ODE Causal Modeling and an Application to Glycemic Response

Bayesian Knowledge Distillation: A Bayesian Perspective of Distillation with Uncertainty Quantification

Reference Neural Operators: Learning the Smooth Dependence of Solutions of PDEs on Geometric Deformations

Efficient Policy Evaluation with Offline Data Informed Behavior Policy Design

Longitudinal Targeted Minimum Loss-based Estimation with Temporal-Difference Heterogeneous Transformer

Non-confusing Generation of Customized Concepts in Diffusion Models

Near-Optimal Regret in Linear MDPs with Aggregate Bandit Feedback

Amortized Equation Discovery in Hybrid Dynamical Systems

SelMatch: Effectively Scaling Up Dataset Distillation via Selection-Based Initialization and Partial Updates by Trajectory Matching

Quantum Theory and Application of Contextual Optimal Transport

Equivariant Diffusion for Crystal Structure Prediction

Leveraging Attractor Dynamics in Spatial Navigation for Better Language Parsing

Generalization in Kernel Regression Under Realistic Assumptions

Two Tales of Single-Phase Contrastive Hebbian Learning

Consistent Submodular Maximization

MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases

Proactive DP: A Multiple Target Optimization Framework for DP-SGD

Distributionally Robust Data Valuation

Spectral Preconditioning for Gradient Methods on Graded Non-convex Functions

Fair Risk Control: A Generalized Framework for Calibrating Multi-group Fairness Risks

Differentially Private Representation Learning via Image Captioning

Do Language Models Exhibit the Same Cognitive Biases in Problem Solving as Human Learners?

Ensemble Pruning for Out-of-distribution Generalization

Bridging Data Gaps in Diffusion Models with Adversarial Noise-Based Transfer Learning

Building Socially-Equitable Public Models

Projecting Molecules into Synthesizable Chemical Spaces

From Geometry to Causality- Ricci Curvature and the Reliability of Causal Inference on Networks

Fast Algorithms for Hypergraph PageRank with Applications to Semi-Supervised Learning

Truly No-Regret Learning in Constrained MDPs

Regression Learning with Limited Observations of Multivariate Outcomes and Features

Autaptic Synaptic Circuit Enhances Spatio-temporal Predictive Learning of Spiking Neural Networks

Watermark Stealing in Large Language Models

SqueezeLLM: Dense-and-Sparse Quantization

Beyond the Norms: Detecting Prediction Errors in Regression Models

OAK: Enriching Document Representations using Auxiliary Knowledge for Extreme Classification

EvTexture: Event-driven Texture Enhancement for Video Super-Resolution

Differentiable Model Scaling using Differentiable Topk

Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations

Trustworthy Actionable Perturbations

Position: Enforced Amnesia as a Way to Mitigate the Potential Risk of Silent Suffering in the Conscious AI

Testing the Feasibility of Linear Programs with Bandit Feedback

Position: Benchmarking is Limited in Reinforcement Learning Research

Switchable Decision: Dynamic Neural Generation Networks

HarmonyDream: Task Harmonization Inside World Models

Sample-Efficient Multiagent Reinforcement Learning with Reset Replay

Reducing sequential change detection to sequential estimation

Realistic Unsupervised CLIP Fine-tuning with Universal Entropy Optimization

Extending Adversarial Attacks to Produce Adversarial Class Probability Distributions

BLO-SAM: Bi-level Optimization Based Finetuning of the Segment Anything Model for Overfitting-Preventing Semantic Segmentation

Conditional Language Learning with Context

Exponential Spectral Pursuit: An Effective Initialization Method for Sparse Phase Retrieval

Towards Resource-friendly, Extensible and Stable Incomplete Multi-view Clustering

Coactive Learning for Large Language Models using Implicit User Feedback

Understanding Retrieval-Augmented Task Adaptation for Vision-Language Models

Drug Discovery with Dynamic Goal-aware Fragments

Designing Decision Support Systems using Counterfactual Prediction Sets

Towards Unified Multi-granularity Text Detection with Interactive Attention

Transforming and Combining Rewards for Aligning Large Language Models

Preventing Model Collapse in Gaussian Process Latent Variable Models

Position: Machine Learning-powered Assessments of the EU Digital Services Act Aid Quantify Policy Impacts on Online Harms

Doubly Robust Causal Effect Estimation under Networked Interference via Targeted Learning

MADA: Meta-Adaptive Optimizers Through Hyper-Gradient Descent

The Illusion of State in State-Space Models

Scaling Rectified Flow Transformers for High-Resolution Image Synthesis

In-Context Language Learning: Architectures and Algorithms

Collective Certified Robustness against Graph Injection Attacks

How Smooth Is Attention?

Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark

An Improved Finite-time Analysis of Temporal Difference Learning with Deep Neural Networks

SLEB: Streamlining LLMs through Redundancy Verification and Elimination of Transformer Blocks

Disparate Impact on Group Accuracy of Linearization for Private Inference

Differentially private exact recovery for stochastic block models

Uncertainty Estimation by Density Aware Evidential Deep Learning

Fair Off-Policy Learning from Observational Data

Sparse Inducing Points in Deep Gaussian Processes: Enhancing Modeling with Denoising Diffusion Variational Inference

Cell2Sentence: Teaching Large Language Models the Language of Biology

On Multi-Armed Bandit with Impatient Arms

PlanDQ: Hierarchical Plan Orchestration via D-Conductor and Q-Performer

Individual Fairness in Graph Decomposition

UPOCR: Towards Unified Pixel-Level OCR Interface

Feature Distribution on Graph Topology Mediates the Effect of Graph Convolution: Homophily Perspective

Implicit Compressibility of Overparametrized Neural Networks Trained with Heavy-Tailed SGD

HGAP: Boosting Permutation Invariant and Permutation Equivariant in Multi-Agent Reinforcement Learning via Graph Attention Network

Parallel Affine Transformation Tuning of Markov Chain Monte Carlo

Boximator: Generating Rich and Controllable Motions for Video Synthesis

Which Frequencies do CNNs Need? Emergent Bottleneck Structure in Feature Learning

tnGPS: Discovering Unknown Tensor Network Structure Search Algorithms via Large Language Models (LLMs)

Physics and Lie symmetry informed Gaussian processes

Bayesian Program Learning by Decompiling Amortized Knowledge

Reservoir Computing for Short High-Dimensional Time Series: an Application to SARS-CoV-2 Hospitalization Forecast

Stable Differentiable Causal Discovery

To Cool or not to Cool? Temperature Network Meets Large Foundation Models via DRO

Online Cascade Learning for Efficient Inference over Streams

Coarse-to-Fine Highlighting: Reducing Knowledge Hallucination in Large Language Models

Probabilistic Conceptual Explainers: Trustworthy Conceptual Explanations for Vision Foundation Models

SAM-E: Leveraging Visual Foundation Model with Sequence Imitation for Embodied Manipulation

Decoupling Learning and Decision-Making: Breaking the $\mathcal{O}(\sqrt{T})$ Barrier in Online Resource Allocation with First-Order Methods

From Neurons to Neutrons: A Case Study in Interpretability

Finite-Time Convergence and Sample Complexity of Actor-Critic Multi-Objective Reinforcement Learning

Hierarchical Integral Probability Metrics: A distance on random probability measures with low sample complexity

RoboMP$^2$: A Robotic Multimodal Perception-Planning Framework with Multimodal Large Language Models

OMPO: A Unified Framework for RL under Policy and Dynamics Shifts

Neural Jump-Diffusion Temporal Point Processes

OLLIE: Imitation Learning from Offline Pretraining to Online Finetuning

Eluder-based Regret for Stochastic Contextual MDPs

Self-Supervised Coarsening of Unstructured Grid with Automatic Differentiation

Challenges and Considerations in the Evaluation of Bayesian Causal Discovery

Evaluation of LLMs on Syntax-Aware Code Fill-in-the-Middle Tasks

Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation

Convex and Bilevel Optimization for Neural-Symbolic Inference and Learning

Do Models Explain Themselves? Counterfactual Simulatability of Natural Language Explanations

Efficient Online Set-valued Classification with Bandit Feedback

Towards Realistic Model Selection for Semi-supervised Learning

Learning to Infer Generative Template Programs for Visual Concepts

E$^2$GAN: Efficient Training of Efficient GANs for Image-to-Image Translation

Auto-Encoding Morph-Tokens for Multimodal LLM

Peeking with PEAK: Sequential, Nonparametric Composite Hypothesis Tests for Means of Multiple Data Streams

Trust the Model Where It Trusts Itself - Model-Based Actor-Critic with Uncertainty-Aware Rollout Adaption

Ameliorate Spurious Correlations in Dataset Condensation

Understanding and Diagnosing Deep Reinforcement Learning

Local Feature Selection without Label or Feature Leakage for Interpretable Machine Learning Predictions

Unleashing the Power of Meta-tuning for Few-shot Generalization Through Sparse Interpolated Experts

Causal Discovery with Fewer Conditional Independence Tests

Improving Accuracy-robustness Trade-off via Pixel Reweighted Adversarial Training

Predicting Dose-Response Curves with Deep Neural Networks

Be Your Own Neighborhood: Detecting Adversarial Examples by the Neighborhood Relations Built on Self-Supervised Learning

Variance-reduced Zeroth-Order Methods for Fine-Tuning Language Models

Distinguishing the Knowable from the Unknowable with Language Models

Position: On the Possibilities of AI-Generated Text Detection

Biharmonic Distance of Graphs and its Higher-Order Variants: Theoretical Properties with Applications to Centrality and Clustering

Catapults in SGD: spikes in the training loss and their impact on generalization through feature learning

Is Inverse Reinforcement Learning Harder than Standard Reinforcement Learning? A Theoretical Perspective

Quality-Weighted Vendi Scores And Their Application To Diverse Experimental Design

Junk DNA Hypothesis: Pruning Small Pre-Trained Weights $\textit{Irreversibly}$ and $\textit{Monotonically}$ Impairs ``Difficult" Downstream Tasks in LLMs

CHAI: Clustered Head Attention for Efficient LLM Inference

Learning Associative Memories with Gradient Descent

Faster Sampling via Stochastic Gradient Proximal Sampler

Random Masking Finds Winning Tickets for Parameter Efficient Fine-tuning

Improving Instruction Following in Language Models through Proxy-Based Uncertainty Estimation

Whispering Experts: Neural Interventions for Toxicity Mitigation in Language Models

Sparse is Enough in Fine-tuning Pre-trained Large Language Models

Non-Vacuous Generalization Bounds for Large Language Models

Graph-based Forecasting with Missing Data through Spatiotemporal Downsampling

Asymptotics of feature learning in two-layer networks after one gradient-step

InstructRetro: Instruction Tuning post Retrieval-Augmented Pretraining

Exploiting Code Symmetries for Learning Program Semantics

Inferring the Long-Term Causal Effects of Long-Term Treatments from Short-Term Experiments

What needs to go right for an induction head? A mechanistic study of in-context learning circuits and their formation

Density Ratio Estimation with Doubly Strong Robustness

SILVER: Single-loop variance reduction and application to federated learning

Online Learning in CMDPs: Handling Stochastic and Adversarial Constraints

Don’t Label Twice: Quantity Beats Quality when Comparing Binary Classifiers on a Budget

Resisting Stochastic Risks in Diffusion Planners with the Trajectory Aggregation Tree

InstructSpeech: Following Speech Editing Instructions via Large Language Models

HyperFields: Towards Zero-Shot Generation of NeRFs from Text

Collage: Light-Weight Low-Precision Strategy for LLM Training

Polygonal Unadjusted Langevin Algorithms: Creating stable and efficient adaptive algorithms for neural networks

Auditing Private Prediction

Is Kernel Prediction More Powerful than Gating in Convolutional Neural Networks?

Score identity Distillation: Exponentially Fast Distillation of Pretrained Diffusion Models for One-Step Generation

Sequential Kernel Goodness-of-fit Testing

Boosting Offline Optimizers with Surrogate Sensitivity

No Free Prune: Information-Theoretic Barriers to Pruning at Initialization

Understanding Inter-Concept Relationships in Concept-Based Models

StyDeSty: Min-Max Stylization and Destylization for Single Domain Generalization

Enhancing Sufficient Dimension Reduction via Hellinger Correlation

Position: Key Claims in LLM Research Have a Long Tail of Footnotes

Detecting and Identifying Selection Structure in Sequential Data

How to Make the Gradients Small Privately: Improved Rates for Differentially Private Non-Convex Optimization

SparQ Attention: Bandwidth-Efficient LLM Inference

EDISON: Enhanced Dictionary-Induced Tensorized Incomplete Multi-View Clustering with Gaussian Error Rank Minimization

Position: AI/ML Influencers Have a Place in the Academic Process

Integrating Multimodal Data for Joint Generative Modeling of Complex Dynamics

Scalable Multiple Kernel Clustering: Learning Clustering Structure from Expectation

Investigating Pre-Training Objectives for Generalization in Vision-Based Reinforcement Learning

Efficient Adaptation in Mixed-Motive Environments via Hierarchical Opponent Modeling and Planning

Can Looped Transformers Learn to Implement Multi-step Gradient Descent for In-context Learning?

Provably Robust DPO: Aligning Language Models with Noisy Feedback

Beyond Chinchilla-Optimal: Accounting for Inference in Language Model Scaling Laws

MathScale: Scaling Instruction Tuning for Mathematical Reasoning

GALA3D: Towards Text-to-3D Complex Scene Generation via Layout-guided Generative Gaussian Splatting

Robust and Conjugate Gaussian Process Regression

Robust Inverse Graphics via Probabilistic Inference

SceneCraft: An LLM Agent for Synthesizing 3D Scenes as Blender Code

Symmetric Matrix Completion with ReLU Sampling

Attribution-based Explanations that Provide Recourse Cannot be Robust

A General Framework for Sequential Decision-Making under Adaptivity Constraints

A2Q+: Improving Accumulator-Aware Weight Quantization

A Human-Inspired Reading Agent with Gist Memory of Very Long Contexts

Interaction-based Retrieval-augmented Diffusion Models for Protein-specific 3D Molecule Generation

Position: Measure Dataset Diversity, Don't Just Claim It

Curated LLM: Synergy of LLMs and Data Curation for tabular augmentation in low-data regimes

Trainable Transformer in Transformer

High-Probability Bound for Non-Smooth Non-Convex Stochastic Optimization with Heavy Tails

Probabilistic Generating Circuits - Demystified

A Graph is Worth $K$ Words: Euclideanizing Graph using Pure Transformer

In-Context Decision Transformer: Reinforcement Learning via Hierarchical Chain-of-Thought

$\mathtt{VITS}$ : Variational Inference Thompson Sampling for contextual bandits

Antibody Design Using a Score-based Diffusion Model Guided by Evolutionary, Physical and Geometric Constraints

Beyond ELBOs: A Large-Scale Evaluation of Variational Methods for Sampling

PhAST: Physics-Aware, Scalable, and Task-Specific GNNs for Accelerated Catalyst Design

DeCoOp: Robust Prompt Tuning with Out-of-Distribution Detection

LPGD: A General Framework for Backpropagation through Embedded Optimization Layers

Online Matching with Stochastic Rewards: Provable Better Bound via Adversarial Reinforcement Learning

A Theory of Fault-Tolerant Learning

High-Performance Temporal Reversible Spiking Neural Networks with $\mathcal{O}(L)$ Training Memory and $\mathcal{O}(1)$ Inference Cost

Beyond Individual Input for Deep Anomaly Detection on Tabular Data

Handling Heterogeneous Curvatures in Bandit LQR Control

Collaborative Heterogeneous Causal Inference Beyond Meta-analysis

Probabilistic Time Series Modeling with Decomposable Denoising Diffusion Model

Successor Features for Efficient Multi-Subject Controlled Text Generation

Reinforcement Learning within Tree Search for Fast Macro Placement

A New Branch-and-Bound Pruning Framework for $\ell_0$-Regularized Problems

Adaptive Feature Selection for No-Reference Image Quality Assessment by Mitigating Semantic Noise Sensitivity

Fool Your (Vision and) Language Model with Embarrassingly Simple Permutations

Towards General Neural Surrogate Solvers with Specialized Neural Accelerators

From Classification Accuracy to Proper Scoring Rules: Elicitability of Probabilistic Top List Predictions

Bridging Environments and Language with Rendering Functions and Vision-Language Models

An Unsupervised Approach for Periodic Source Detection in Time Series

Learning Linear Block Error Correction Codes

Integrated Hardware Architecture and Device Placement Search

UniAudio: Towards Universal Audio Generation with Large Language Models

Mobile Attention: Mobile-Friendly Linear-Attention for Vision Transformers

Federated Neuro-Symbolic Learning

MagicPose: Realistic Human Poses and Facial Expressions Retargeting with Identity-aware Diffusion

Efficient Precision and Recall Metrics for Assessing Generative Models using Hubness-aware Sampling

GATE: How to Keep Out Intrusive Neighbors

Learning Solution-Aware Transformers for Efficiently Solving Quadratic Assignment Problem

(ends 4:00 AM)

3:30 a.m.

Break:

Hosted Lunch

(ends 5:00 AM)

4:30 a.m.

Poster Session 4 [4:30-6:00]

Posters 4:30-6:00

QUEST: Query-Aware Sparsity for Efficient Long-Context LLM Inference

Centralized Selection with Preferences in the Presence of Biases

Harnessing Hierarchical Label Distribution Variations in Test Agnostic Long-tail Recognition

Optimal Hessian/Jacobian-Free Nonconvex-PL Bilevel Optimization

Model-based Reinforcement Learning for Parameterized Action Spaces

Flora: Low-Rank Adapters Are Secretly Gradient Compressors

PcLast: Discovering Plannable Continuous Latent States

Extracting Training Data From Document-Based VQA Models

Dissecting Multimodality in VideoQA Transformer Models by Impairing Modality Fusion

Stop Regressing: Training Value Functions via Classification for Scalable Deep RL

Position: Fundamental Limitations of LLM Censorship Necessitate New Approaches

Operator SVD with Neural Networks via Nested Low-Rank Approximation

Plug-and-Play image restoration with Stochastic deNOising REgularization

Self-Attention through Kernel-Eigen Pair Sparse Variational Gaussian Processes

Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels

Trained Random Forests Completely Reveal your Dataset

SCoRe: Submodular Combinatorial Representation Learning

Posterior Sampling-Based Bayesian Optimization with Tighter Bayesian Regret Bounds

Multi-Factor Adaptive Vision Selection for Egocentric Video Question Answering

Memorization Through the Lens of Curvature of Loss Function Around Samples

State-Free Inference of State-Space Models: The *Transfer Function* Approach

Accelerating Iterative Retrieval-augmented Language Model Serving with Speculation

A Multimodal Automated Interpretability Agent

Latent Space Symmetry Discovery

SciBench: Evaluating College-Level Scientific Problem-Solving Abilities of Large Language Models

SAM as the Guide: Mastering Pseudo-Label Refinement in Semi-Supervised Referring Expression Segmentation

On the Tractability of SHAP Explanations under Markovian Distributions

Convergence of Some Convex Message Passing Algorithms to a Fixed Point

Learning High-Frequency Functions Made Easy with Sinusoidal Positional Encoding

Optimal Batched Linear Bandits

Unveiling the Cycloid Trajectory of EM Iterations in Mixed Linear Regression

Gaussian Plane-Wave Neural Operator for Electron Density Estimation

No Wrong Turns: The Simple Geometry Of Neural Networks Optimization Paths

Uncertainty for Active Learning on Graphs

Language Models with Conformal Factuality Guarantees

Balanced Data, Imbalanced Spectra: Unveiling Class Disparities with Spectral Imbalance

A Sober Look at LLMs for Material Discovery: Are They Actually Good for Bayesian Optimization Over Molecules?

Self-attention Networks Localize When QK-eigenspectrum Concentrates

Multi-Agent Reinforcement Learning with Hierarchical Coordination for Emergency Responder Stationing

Adaptive Learning of Density Ratios in RKHS

Simple linear attention language models balance the recall-throughput tradeoff

One Size Fits All for Semantic Shifts: Adaptive Prompt Tuning for Continual Learning

When Representations Align: Universality in Representation Learning Dynamics

Meta-Reinforcement Learning Robust to Distributional Shift Via Performing Lifelong In-Context Learning

INViT: A Generalizable Routing Problem Solver with Invariant Nested View Transformer

CLIF: Complementary Leaky Integrate-and-Fire Neuron for Spiking Neural Networks

Harmony in Diversity: Merging Neural Networks with Canonical Correlation Analysis

Attention Meets Post-hoc Interpretability: A Mathematical Perspective

Algorithmic Stability Unleashed: Generalization Bounds with Unbounded Losses

Federated Combinatorial Multi-Agent Multi-Armed Bandits

Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality

Revisiting the Power of Prompt for Visual Tuning

ESNet: Evolution and Succession Network for High-Resolution Salient Object Detection

Learning Reward for Robot Skills Using Large Language Models via Self-Alignment

Comparing Graph Transformers via Positional Encodings

ExCP: Extreme LLM Checkpoint Compression via Weight-Momentum Joint Shrinking

On Mechanistic Knowledge Localization in Text-to-Image Generative Models

Soft Prompt Recovers Compressed LLMs, Transferably

A Primal-Dual Algorithm for Offline Constrained Reinforcement Learning with Linear MDPs

Learning Optimal Projection for Forecast Reconciliation of Hierarchical Time Series

Combinatorial Approximations for Cluster Deletion: Simpler, Faster, and Better

Multi-Source Conformal Inference Under Distribution Shift

Transformers, parallel computation, and logarithmic depth

To Each (Textual Sequence) Its Own: Improving Memorized-Data Unlearning in Large Language Models

Prompting is a Double-Edged Sword: Improving Worst-Group Robustness of Foundation Models

Causal Representation Learning Made Identifiable by Grouping of Observational Variables

Bottleneck-Minimal Indexing for Generative Document Retrieval

Compress Clean Signal from Noisy Raw Image: A Self-Supervised Approach

Provably Efficient Reinforcement Learning for Adversarial Restless Multi-Armed Bandits with Unknown Transitions and Bandit Feedback

A Unified Adaptive Testing System Enabled by Hierarchical Structure Search

Balanced Resonate-and-Fire Neurons

PAPM: A Physics-aware Proxy Model for Process Systems

Language-Driven Cross-Modal Classifier for Zero-Shot Multi-Label Image Recognition

Large Language Models Can Automatically Engineer Features for Few-Shot Tabular Learning

Ambiguity-Aware Abductive Learning

AquaLoRA: Toward White-box Protection for Customized Stable Diffusion Models via Watermark LoRA

Geometric Active Exploration in Markov Decision Processes: the Benefit of Abstraction

On the Nonlinearity of Layer Normalization

Representing Molecules as Random Walks Over Interpretable Grammars

Statistical Inference Under Constrained Selection Bias

Convergence and Complexity Guarantee for Inexact First-order Riemannian Optimization Algorithms

Position: Future Directions in the Theory of Graph Machine Learning

Accelerated Policy Gradient for s-rectangular Robust MDPs with Large State Spaces

Multi-Fidelity Residual Neural Processes for Scalable Surrogate Modeling

The Role of Learning Algorithms in Collective Action

Surface-VQMAE: Vector-quantized Masked Auto-encoders on Molecular Surfaces

Towards a Self-contained Data-driven Global Weather Forecasting Framework

LLM and Simulation as Bilevel Optimizers: A New Paradigm to Advance Physical Scientific Discovery

Projection-Free Online Convex Optimization with Time-Varying Constraints

Deletion-Anticipative Data Selection with a Limited Budget

Plug-in Performative Optimization

Efficient Denoising Diffusion via Probabilistic Masking

Adaptive Horizon Actor-Critic for Policy Learning in Contact-Rich Differentiable Simulation

Characterizing Large Language Model Geometry Helps Solve Toxicity Detection and Generation

Riemannian Accelerated Zeroth-order Algorithm: Improved Robustness and Lower Query Complexity

Intersectional Unfairness Discovery

$H$-Consistency Guarantees for Regression

Run-Time Task Composition with Safety Semantics

SignSGD with Federated Defense: Harnessing Adversarial Attacks through Gradient Sign Decoding

GenCO: Generating Diverse Designs with Combinatorial Constraints

Not Just Pretty Pictures: Toward Interventional Data Augmentation Using Text-to-Image Generators

Interpretability Illusions in the Generalization of Simplified Models

Reparameterized Importance Sampling for Robust Variational Bayesian Neural Networks

Automated Evaluation of Retrieval-Augmented Language Models with Task-Specific Exam Generation

Erasing the Bias: Fine-Tuning Foundation Models for Semi-Supervised Learning

Position: Leverage Foundational Models for Black-Box Optimization

BECoTTA: Input-dependent Online Blending of Experts for Continual Test-time Adaptation

IM-3D: Iterative Multiview Diffusion and Reconstruction for High-Quality 3D Generation

Mollification Effects of Policy Gradient Methods

PGODE: Towards High-quality System Dynamics Modeling

Interplay of ROC and Precision-Recall AUCs: Theoretical Limits and Practical Implications in Binary Classification

PEARL: Zero-shot Cross-task Preference Alignment and Robust Reward Learning for Robotic Manipulation

AutoOS: Make Your OS More Powerful by Exploiting Large Language Models

A Bayesian Approach to Online Planning

AST-T5: Structure-Aware Pretraining for Code Generation and Understanding

Learning 1-Bit Tiny Object Detector with Discriminative Feature Refinement

Scalable Safe Policy Improvement for Factored Multi-Agent MDPs

Sobolev Space Regularised Pre Density Models

Feedback Efficient Online Fine-Tuning of Diffusion Models

Robust Yet Efficient Conformal Prediction Sets

Long-Tail Learning with Foundation Model: Heavy Fine-Tuning Hurts

Rethinking Optimization and Architecture for Tiny Language Models

Mean Estimation in the Add-Remove Model of Differential Privacy

Zeroth-Order Methods for Constrained Nonconvex Nonsmooth Stochastic Optimization

Conformal Prediction Sets Improve Human Decision Making

Breaking through the learning plateaus of in-context learning in Transformer

Algorithm of Thoughts: Enhancing Exploration of Ideas in Large Language Models

Iterative Data Smoothing: Mitigating Reward Overfitting and Overoptimization in RLHF

Data-free Distillation of Diffusion Models with Bootstrapping

Improving Antibody Humanness Prediction using Patent Data

Flexible Residual Binarization for Image Super-Resolution

Position: Stop Making Unscientific AGI Performance Claims

Simplicity Bias via Global Convergence of Sharpness Minimization

In-Context Reinforcement Learning for Variable Action Spaces

Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustment

Position: Intent-aligned AI Systems Must Optimize for Agency Preservation

Efficient and Effective Time-Series Forecasting with Spiking Neural Networks

Online Learning and Information Exponents: The Importance of Batch size & Time/Complexity Tradeoffs

Sparse Dimensionality Reduction Revisited

Equivariant Graph Neural Operator for Modeling 3D Dynamics

Timer: Generative Pre-trained Transformers Are Large Time Series Models

A connection between Tempering and Entropic Mirror Descent

Hidden Traveling Waves bind Working Memory Variables in Recurrent Neural Networks

On the Calibration of Human Pose Estimation

Robust Universal Adversarial Perturbations

Overestimation, Overfitting, and Plasticity in Actor-Critic: the Bitter Lesson of Reinforcement Learning

ETHER: Efficient Finetuning of Large-Scale Models with Hyperplane Reflections

How Uniform Random Weights Induce Non-uniform Bias: Typical Interpolating Neural Networks Generalize with Narrow Teachers

Bespoke Non-Stationary Solvers for Fast Sampling of Diffusion and Flow Models

Universal Consistency of Wide and Deep ReLU Neural Networks and Minimax Optimal Convergence Rates for Kolmogorov-Donoho Optimal Function Classes

Differentiability and Optimization of Multiparameter Persistent Homology

Remembering to Be Fair: Non-Markovian Fairness in Sequential Decision Making

Fair Federated Learning via the Proportional Veto Core

Towards Causal Foundation Model: on Duality between Optimal Balancing and Attention

To the Max: Reinventing Reward in Reinforcement Learning

Tilt your Head: Activating the Hidden Spatial-Invariance of Classifiers

Iterated Denoising Energy Matching for Sampling from Boltzmann Densities

Locally Estimated Global Perturbations are Better than Local Perturbations for Federated Sharpness-aware Minimization

Characterizing ResNet's Universal Approximation Capability

Visual-Text Cross Alignment: Refining the Similarity Score in Vision-Language Models

SpikeLM: Towards General Spike-Driven Language Modeling via Elastic Bi-Spiking Mechanisms

Graphon Mean Field Games with a Representative Player: Analysis and Learning Algorithm

On the Asymptotic Distribution of the Minimum Empirical Risk

DetKDS: Knowledge Distillation Search for Object Detectors

Smoothing Proximal Gradient Methods for Nonsmooth Sparsity Constrained Optimization: Optimality Conditions and Global Convergence

In value-based deep reinforcement learning, a pruned network is a good network

Position: Do pretrained Transformers Learn In-Context by Gradient Descent?

Online Learning under Budget and ROI Constraints via Weak Adaptivity

Guiding LLMs The Right Way: Fast, Non-Invasive Constrained Generation

Towards the Theory of Unsupervised Federated Learning: Non-asymptotic Analysis of Federated EM Algorithms

Policy-conditioned Environment Models are More Generalizable

Rate-Optimal Policy Optimization for Linear Markov Decision Processes

Tilt and Average : Geometric Adjustment of the Last Layer for Recalibration

What Can Transformer Learn with Varying Depth? Case Studies on Sequence Learning Tasks

Projection-Free Variance Reduction Methods for Stochastic Constrained Multi-Level Compositional Optimization

ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL

Understanding the Impact of Introducing Constraints at Inference Time on Generalization Error

MLAgentBench: Evaluating Language Agents on Machine Learning Experimentation

Wasserstein Wormhole: Scalable Optimal Transport Distance with Transformer

PICLe: Eliciting Diverse Behaviors from Large Language Models with Persona In-Context Learning

Speech Self-Supervised Learning Using Diffusion Model Synthetic Data

Random matrix theory improved Fréchet mean of symmetric positive definite matrices

Candidate Pseudolabel Learning: Enhancing Vision-Language Models by Prompt Tuning with Unlabeled Data

Guidance with Spherical Gaussian Constraint for Conditional Diffusion

Token-level Direct Preference Optimization

Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast

Position: Scaling Simulation is Neither Necessary Nor Sufficient for In-the-Wild Robot Manipulation

Intersecting-Boundary-Sensitive Fingerprinting for Tampering Detection of DNN Models

Certifiably Byzantine-Robust Federated Conformal Prediction

Learning a Diffusion Model Policy from Rewards via Q-Score Matching

Promises and Pitfalls of Generative Masked Language Modeling: Theoretical Framework and Practical Guidelines

Generalization Analysis of Stochastic Weight Averaging with General Sampling

Learning Decision Policies with Instrumental Variables through Double Machine Learning

Extending Test-Time Augmentation with Metamorphic Relations for Combinatorial Problems

Dynamic Correlation Clustering in Sublinear Update Time

Agnostic Learning of Mixed Linear Regressions with EM and AM Algorithms

Contrastive Representation for Data Filtering in Cross-Domain Offline Reinforcement Learning

Compute Better Spent: Replacing Dense Layers with Structured Matrices

Is Temperature Sample Efficient for Softmax Gaussian Mixture of Experts?

Better Safe than Sorry: Pre-training CLIP against Targeted Data Poisoning and Backdoor Attacks

MagicLens: Self-Supervised Image Retrieval with Open-Ended Instructions

Cooperative Graph Neural Networks

ERQ: Error Reduction for Post-Training Quantization of Vision Transformers

Explain Temporal Black-Box Models via Functional Decomposition

Noise-Adaptive Confidence Sets for Linear Bandits and Application to Bayesian Optimization

Graph2Tac: Online Representation Learning of Formal Math Concepts

Evolving Subnetwork Training for Large Language Models

Learning Latent Dynamic Robust Representations for World Models

Defining Neural Network Architecture through Polytope Structures of Datasets

EVEREST: Efficient Masked Video Autoencoder by Removing Redundant Spatiotemporal Tokens

Theory of Consistency Diffusion Models: Distribution Estimation Meets Fast Sampling

Craftax: A Lightning-Fast Benchmark for Open-Ended Reinforcement Learning

No Double Descent in Principal Component Regression: A High-Dimensional Analysis

A Theoretical Analysis of Backdoor Poisoning Attacks in Convolutional Neural Networks

Meta-Learners for Partially-Identified Treatment Effects Across Multiple Environments

Position: An Inner Interpretability Framework for AI Inspired by Lessons from Cognitive Neuroscience

Stability and Generalization for Stochastic Recursive Momentum-based Algorithms for (Strongly-)Convex One to $K$-Level Stochastic Optimizations

Few-Shot Character Understanding in Movies as an Assessment to Meta-Learning of Theory-of-Mind

Confidence Aware Inverse Constrained Reinforcement Learning

Learning Divergence Fields for Shift-Robust Graph Representations

Modelling Microbial Communities with Graph Neural Networks

Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce for Pruning LLMs to High Sparsity

Flextron: Many-in-One Flexible Large Language Model

Algorithm and Hardness for Dynamic Attention Maintenance in Large Language Models

Planning, Fast and Slow: Online Reinforcement Learning with Action-Free Offline Data via Multiscale Planners

TERD: A Unified Framework for Safeguarding Diffusion Models Against Backdoors

Fast Decision Boundary based Out-of-Distribution Detector

CurBench: Curriculum Learning Benchmark

Enhancing Cross-Modal Fine-Tuning with Gradually Intermediate Modality Generation

Factored-Reward Bandits with Intermediate Observations

Retrieval Across Any Domains via Large-scale Pre-trained Model

Towards Efficient Spiking Transformer: a Token Sparsification Framework for Training and Inference Acceleration

Graph Neural Stochastic Diffusion for Estimating Uncertainty in Node Classification

VNN: Verification-Friendly Neural Networks with Hard Robustness Guarantees

MEMORYLLM: Towards Self-Updatable Large Language Models

Hierarchical State Space Models for Continuous Sequence-to-Sequence Modeling

CogBench: a large language model walks into a psychology lab

Understanding Heterophily for Graph Neural Networks

Keep the Momentum: Conservation Laws beyond Euclidean Gradient Flows

Uncertainty-Aware Reward-Free Exploration with General Function Approximation

Large Scale Dataset Distillation with Domain Shift

Orthogonal Bootstrap: Efficient Simulation of Input Uncertainty

Beyond the Calibration Point: Mechanism Comparison in Differential Privacy

Quality-Diversity with Limited Resources

A Simple Early Exiting Framework for Accelerated Sampling in Diffusion Models

Discovering Features with Synergistic Interactions in Multiple Views

Lie Neurons: Adjoint-Equivariant Neural Networks for Semisimple Lie Algebras

NExT: Teaching Large Language Models to Reason about Code Execution

Randomized Confidence Bounds for Stochastic Partial Monitoring

MusicRL: Aligning Music Generation to Human Preferences

Nonlinear Filtering with Brenier Optimal Transport Maps

Sliding Down the Stairs: How Correlated Latent Variables Accelerate Learning with Neural Networks

MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities

Emergence of In-Context Reinforcement Learning from Noise Distillation

Self-Alignment of Large Language Models via Monopolylogue-based Social Scene Simulation

A Computational Framework for Solving Wasserstein Lagrangian Flows

Optimal Acceleration for Minimax and Fixed-Point Problems is Not Unique

Equivariant Frames and the Impossibility of Continuous Canonicalization

Differentially Private Sum-Product Networks

DiracDiffusion: Denoising and Incremental Reconstruction with Assured Data-Consistency

Measures of diversity and space-filling designs for categorical data

In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering

High-dimensional Linear Bandits with Knapsacks

A Geometric Decomposition of Finite Games: Convergence vs. Recurrence under Exponential Weights

Offline Actor-Critic Reinforcement Learning Scales to Large Models

An Information Theoretic Approach to Interaction-Grounded Learning

Structure Your Data: Towards Semantic Graph Counterfactuals

Double Stochasticity Gazes Faster: Snap-Shot Decentralized Stochastic Gradient Tracking Methods

Benchmarking and Building Long-Context Retrieval Models with LoCo and M2-BERT

Position: Evolving AI Collectives Enhance Human Diversity and Enable Self-Regulation

Sampling in Unit Time with Kernel Fisher-Rao Flow

Causal Effect Identification in LiNGAM Models with Latent Confounders

MaxMin-RLHF: Alignment with Diverse Human Preferences

PID: Prompt-Independent Data Protection Against Latent Diffusion Models

Experts Don't Cheat: Learning What You Don't Know By Predicting Pairs

Using Uncertainty Quantification to Characterize and Improve Out-of-Domain Learning for PDEs

Stealing part of a production language model

Positive and Unlabeled Learning with Controlled Probability Boundary Fence

A Distributional Analogue to the Successor Representation

Transformers Provably Learn Sparse Token Selection While Fully-Connected Nets Cannot

Learning Pseudo-Contractive Denoisers for Inverse Problems

xT: Nested Tokenization for Larger Context in Large Images

Pseudo-Calibration: Improving Predictive Uncertainty Estimation in Unsupervised Domain Adaptation

Position: Mission Critical – Satellite Data is a Distinct Modality in Machine Learning

On Prompt-Driven Safeguarding for Large Language Models

Deeper or Wider: A Perspective from Optimal Generalization Error with Sobolev Loss

CLLMs: Consistency Large Language Models

Delaunay Graph: Addressing Over-Squashing and Over-Smoothing Using Delaunay Triangulation

Beyond Implicit Bias: The Insignificance of SGD Noise in Online Learning

Implicit Bias of Policy Gradient in Linear Quadratic Control: Extrapolation to Unseen Initial States

Non-parametric Online Change Point Detection on Riemannian Manifolds

Short-Long Convolutions Help Hardware-Efficient Linear Attention to Focus on Long Sequences

On the Weight Dynamics of Deep Normalized Networks

Discrete Latent Perspective Learning for Segmentation and Detection

$\bf{\Phi}_\textrm{Flow}$: Differentiable Simulations for PyTorch, TensorFlow and Jax

Faster Streaming and Scalable Algorithms for Finding Directed Dense Subgraphs in Large Graphs

Nearest Neighbour Score Estimators for Diffusion Generative Models

Exact Conversion of In-Context Learning to Model Weights in Linearized-Attention Transformers

InfoNet: Neural Estimation of Mutual Information without Test-Time Optimization

MF-CLR: Multi-Frequency Contrastive Learning Representation for Time Series

Compositional Image Decomposition with Diffusion Models

Efficient Exploration in Average-Reward Constrained Reinforcement Learning: Achieving Near-Optimal Regret With Posterior Sampling

See More Details: Efficient Image Super-Resolution by Experts Mining

Prompting a Pretrained Transformer Can Be a Universal Approximator

Robust Inverse Constrained Reinforcement Learning under Model Misspecification

Tackling Prevalent Conditions in Unsupervised Combinatorial Optimization: Cardinality, Minimum, Covering, and More

Efficient Value Iteration for s-rectangular Robust Markov Decision Processes

Nash Incentive-compatible Online Mechanism Learning via Weakly Differentially Private Online Learning

AI Alignment with Changing and Influenceable Reward Functions

The Surprising Effectiveness of Skip-Tuning in Diffusion Sampling

How Transformers Learn Causal Structure with Gradient Descent

Editing Partially Observable Networks via Graph Diffusion Models

Stability and Multigroup Fairness in Ranking with Uncertain Predictions

Non-clairvoyant Scheduling with Partial Predictions

Improving Gradient-Guided Nested Sampling for Posterior Inference

Larimar: Large Language Models with Episodic Memory Control

Estimating Unknown Population Sizes Using the Hypergeometric Distribution

Monotone Individual Fairness

Demystifying SGD with Doubly Stochastic Gradients

The Fundamental Limits of Least-Privilege Learning

Stochastic Interpolants with Data-Dependent Couplings

Kepler codebook

Understanding the Training Speedup from Sampling with Approximate Losses

Stochastic Conditional Diffusion Models for Robust Semantic Image Synthesis

DRCT: Diffusion Reconstruction Contrastive Training towards Universal Detection of Diffusion Generated Images

Deep Functional Factor Models: Forecasting High-Dimensional Functional Time Series via Bayesian Nonparametric Factorization

Diffusion-based Missing-view Generation With the Application on Incomplete Multi-view Clustering

Delving into Differentially Private Transformer

Winner-takes-all learners are geometry-aware conditional density estimators

Causal Customer Churn Analysis with Low-rank Tensor Block Hazard Model

Reinforcement Learning from Reachability Specifications: PAC Guarantees with Expected Conditional Distance

Detecting Influence Structures in Multi-Agent Reinforcement Learning

Repoformer: Selective Retrieval for Repository-Level Code Completion

3D-VLA: A 3D Vision-Language-Action Generative World Model

MC-GTA: Metric-Constrained Model-Based Clustering using Goodness-of-fit Tests with Autocorrelations

Understanding Adam Optimizer via Online Learning of Updates: Adam is FTRL in Disguise

Diffuse, Sample, Project: Plug-And-Play Controllable Graph Generation

Implicit Representations for Constrained Image Segmentation

A decoder-only foundation model for time-series forecasting

LeaPformer: Enabling Linear Transformers for Autoregressive and Simultaneous Tasks via Learned Proportions

CATS: Enhancing Multivariate Time Series Forecasting by Constructing Auxiliary Time Series as Exogenous Variables

Model-based Reinforcement Learning for Confounded POMDPs

Reducing Balancing Error for Causal Inference via Optimal Transport

FuRL: Visual-Language Models as Fuzzy Rewards for Reinforcement Learning

Evaluating Quantized Large Language Models

Jacobian Regularizer-based Neural Granger Causality

Learning Cognitive Maps from Transformer Representations for Efficient Planning in Partially Observed Environments

Hyperbolic Active Learning for Semantic Segmentation under Domain Shift

Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch

Memory Efficient Neural Processes via Constant Memory Attention Block

Local vs. Global Interpretability: A Computational Complexity Perspective

Exploring Intrinsic Dimension for Vision-Language Model Pruning

Understanding Unimodal Bias in Multimodal Deep Linear Networks

Principled Preferential Bayesian Optimization

How do Large Language Models Navigate Conflicts between Honesty and Helpfulness?

Disentangled 3D Scene Generation with Layout Learning

LoRA+: Efficient Low Rank Adaptation of Large Models

How to Trace Latent Generative Model Generated Images without Artificial Watermark?

Reweighted Solutions for Weighted Low Rank Approximation

Characterizing Overfitting in Kernel Ridgeless Regression Through the Eigenspectrum

Decoding Compressed Trust: Scrutinizing the Trustworthiness of Efficient LLMs Under Compression

Generalization Analysis for Multi-Label Learning

What Improves the Generalization of Graph Transformers? A Theoretical Dive into the Self-attention and Positional Encoding

Learning-Rate-Free Stochastic Optimization over Riemannian Manifolds

GPT-4V(ision) is a Generalist Web Agent, if Grounded

A Unified Linear Programming Framework for Offline Reward Learning from Human Demonstrations and Feedback

Adaptive Accompaniment with ReaLchords

Finite Time Logarithmic Regret Bounds for Self-Tuning Regulation

Low-Cost High-Power Membership Inference Attacks

Compact Optimality Verification for Optimization Proxies

Highway Value Iteration Networks

Performance Bounds for Active Binary Testing with Information Maximization

O$n$ Learning Deep O($n$)-Equivariant Hyperspheres

Manifold Integrated Gradients: Riemannian Geometry for Feature Attribution

MD tree: a model-diagnostic tree grown on loss landscape

Exact Soft Analytical Side-Channel Attacks using Tractable Circuits

Deep Fusion: Efficient Network Training via Pre-trained Initializations

Mind the Boundary: Coreset Selection via Reconstructing the Decision Boundary

Advancing DRL Agents in Commercial Fighting Games: Training, Integration, and Agent-Human Alignment

Neural-Kernel Conditional Mean Embeddings

LQER: Low-Rank Quantization Error Reconstruction for LLMs

PAC-Bayesian Generalization Bounds for Knowledge Graph Representation Learning

PerceptAnon: Exploring the Human Perception of Image Anonymization Beyond Pseudonymization for GDPR

Federated Optimization with Doubly Regularized Drift Correction

UniCorn: A Unified Contrastive Learning Approach for Multi-view Molecular Representation Learning

TimeX++: Learning Time-Series Explanations with Information Bottleneck

SAPG: Split and Aggregate Policy Gradients

Performative Prediction with Bandit Feedback: Learning through Reparameterization

Reason for Future, Act for Now: A Principled Architecture for Autonomous LLM Agents

Indirectly Parameterized Concrete Autoencoders

Connecting the Dots: Is Mode-Connectedness the Key to Feasible Sample-Based Inference in Bayesian Neural Networks?

Stability-Informed Initialization of Neural Ordinary Differential Equations

Progressive Inference: Explaining Decoder-Only Sequence Classification Models Using Intermediate Predictions

Effect-Invariant Mechanisms for Policy Generalization

Closing the Gap: Achieving Global Convergence (Last Iterate) of Actor-Critic under Markovian Sampling with Neural Network Parametrization

PriorBoost: An Adaptive Algorithm for Learning from Aggregate Responses

Off-policy Evaluation Beyond Overlap: Sharp Partial Identification Under Smoothness

A Space Group Symmetry Informed Network for O(3) Equivariant Crystal Tensor Prediction

DISCRET: Synthesizing Faithful Explanations For Treatment Effect Estimation

The Pitfalls and Promise of Conformal Inference Under Adversarial Attacks

Imitation Learning from Purified Demonstrations

Graph Geometry-Preserving Autoencoders

A3S: A General Active Clustering Method with Pairwise Constraints

AI Control: Improving Safety Despite Intentional Subversion

Mean-field Underdamped Langevin Dynamics and its Spacetime Discretization

Image Hijacks: Adversarial Images can Control Generative Models at Runtime

Position: Why We Must Rethink Empirical Research in Machine Learning

VisionGraph: Leveraging Large Multimodal Models for Graph Theory Problems in Visual Context

FrameQuant: Flexible Low-Bit Quantization for Transformers

An Embodied Generalist Agent in 3D World

Tackling Non-Stationarity in Reinforcement Learning via Causal-Origin Representation

Multi-group Learning for Hierarchical Groups

Predictive Coding beyond Correlations

Structured Chemistry Reasoning with Large Language Models

BAGEL: Bootstrapping Agents by Guiding Exploration with Language

Scalable Pre-training of Large Autoregressive Image Models

Improving Adversarial Energy-Based Model via Diffusion Process

Training-Free Long-Context Scaling of Large Language Models

COPAL: Continual Pruning in Large Language Generative Models

Balancing Feature Similarity and Label Variability for Optimal Size-Aware One-shot Subset Selection

Position: Data-driven Discovery with Large Generative Models

Online Learning with Bounded Recall

Linear Alignment: A Closed-form Solution for Aligning Human Preferences without Tuning and Feedback

Differentially Private Bias-Term Fine-tuning of Foundation Models

Modeling Language Tokens as Functionals of Semantic Fields

Graph As Point Set

Rethinking Adversarial Robustness in the Context of the Right to be Forgotten

CCM: Real-Time Controllable Visual Content Creation Using Text-to-Image Consistency Models

CodeIt: Self-Improving Language Models with Prioritized Hindsight Replay

MAGDi: Structured Distillation of Multi-Agent Interaction Graphs Improves Reasoning in Smaller Language Models

(ends 6:00 AM)

6 a.m.

Invited Talk:

Javier Duarte

(ends 7:00 AM)

7 a.m.

Break:

Coffee Break

(ends 7:30 AM)

7:30 a.m.

Oral 4x Optimization 1 [7:30-8:30]

Orals 7:30-8:30

[7:30] InfoNet: Neural Estimation of Mutual Information without Test-Time Optimization

[7:45] Optimal Hessian/Jacobian-Free Nonconvex-PL Bilevel Optimization

[8:00] Principled Preferential Bayesian Optimization

[8:15] Zeroth-Order Methods for Constrained Nonconvex Nonsmooth Stochastic Optimization

(ends 8:30 AM)

Oral 4x Reinforcement Learning 2 [7:30-8:30]

Orals 7:30-8:30

[7:30] Offline Actor-Critic Reinforcement Learning Scales to Large Models

[7:45] Stop Regressing: Training Value Functions via Classification for Scalable Deep RL

[8:00] SAPG: Split and Aggregate Policy Gradients

[8:15] Rate-Optimal Policy Optimization for Linear Markov Decision Processes

(ends 8:30 AM)

Oral 4x Safety and Control [7:30-8:30]

Orals 7:30-8:30

[7:30] Stealing part of a production language model

[7:45] Trained Random Forests Completely Reveal your Dataset

[8:00] AI Control: Improving Safety Despite Intentional Subversion

[8:15] Low-Cost High-Power Membership Inference Attacks

(ends 8:30 AM)

Oral 4x Retrieval [7:30-8:30]

Orals 7:30-8:30

[7:30] Automated Evaluation of Retrieval-Augmented Language Models with Task-Specific Exam Generation

[7:45] MagicLens: Self-Supervised Image Retrieval with Open-Ended Instructions

[8:00] Repoformer: Selective Retrieval for Repository-Level Code Completion

[8:15] Bottleneck-Minimal Indexing for Generative Document Retrieval

(ends 8:30 AM)

Oral 4x LLMs [7:30-8:30]

Orals 7:30-8:30

[7:30] Position: Do pretrained Transformers Learn In-Context by Gradient Descent?

[7:45] ExCP: Extreme LLM Checkpoint Compression via Weight-Momentum Joint Shrinking

[8:00] How do Large Language Models Navigate Conflicts between Honesty and Helpfulness?

[8:15] Flextron: Many-in-One Flexible Large Language Model

(ends 8:30 AM)

Oral 4x Labels [7:30-8:30]

Orals 7:30-8:30

[7:30] Does Label Smoothing Help Deep Partial Label Learning?

[7:45] SAM as the Guide: Mastering Pseudo-Label Refinement in Semi-Supervised Referring Expression Segmentation

[8:00] Candidate Pseudolabel Learning: Enhancing Vision-Language Models by Prompt Tuning with Unlabeled Data

[8:15] Speech Self-Supervised Learning Using Diffusion Model Synthetic Data

(ends 8:30 AM)

11:30 p.m.

Registration

(ends 9:00 AM)

THU 25 JUL

midnight

Invited Talk:

Chelsea Finn

(ends 1:00 AM)

1 a.m.

Break:

Coffee Break

(ends 1:30 AM)

1:30 a.m.

Oral 5x Optimization 2 [1:30-2:30]

Orals 1:30-2:30

[1:30] On the Last-Iterate Convergence of Shuffling Gradient Methods

[1:45] Multiplicative Weights Update, Area Convexity and Random Coordinate Descent for Densest Subgraph Problems

[2:00] High-Probability Convergence for Composite and Distributed Stochastic Minimization and Variational Inequalities with Heavy-Tailed Noise

[2:15] Information Complexity of Stochastic Convex Optimization: Applications to Generalization, Memorization, and Tracing

(ends 2:30 AM)

Oral 5x Heuristics and Algorithms [1:30-2:30]

Orals 1:30-2:30

[1:30] Position: Rethinking Post-Hoc Search-Based Neural Approaches for Solving Large-Scale Traveling Salesman Problems

[1:45] Evolution of Heuristics: Towards Efficient Automatic Algorithm Design Using Large Language Model

[2:00] S$\Omega$I: Score-based O-INFORMATION Estimation

[2:15] A Dynamic Algorithm for Weighted Submodular Cover Problem

(ends 2:30 AM)

Oral 5x Physics in ML [1:30-2:30]

Orals 1:30-2:30

[1:30] Position: Opportunities Exist for Machine Learning in Magnetic Fusion Energy

[1:45] Locality-Sensitive Hashing-Based Efficient Point Transformer with Applications in High-Energy Physics

[2:00] Parameterized Physics-informed Neural Networks for Parameterized PDEs

[2:15] Challenges in Training PINNs: A Loss Landscape Perspective

(ends 2:30 AM)

Oral 5x Continuous Learning [1:30-2:30]

Orals 1:30-2:30

[1:30] PRISE: LLM-Style Sequence Compression for Learning Temporal Action Abstractions in Control

[1:45] Fast Co-Training under Weak Dependence via Stream-Based Active Learning

[2:00] Self-Composing Policies for Scalable Continual Reinforcement Learning

[2:15] Stereo Risk: A Continuous Modeling Approach to Stereo Matching

(ends 2:30 AM)

Oral 5x Distribution Shift and OOD [1:30-2:30]

Orals 1:30-2:30

[1:30] Theoretical Analysis of Learned Database Operations under Distribution Shift through Distribution Learnability

[1:45] Discovering Environments with XRM

[2:00] LCA-on-the-Line: Benchmarking Out of Distribution Generalization with Class Taxonomies

[2:15] Test-Time Model Adaptation with Only Forward Passes

(ends 2:30 AM)

Oral 5x Ensembles [1:30-2:30]

Orals 1:30-2:30

[1:30] Emergent Equivariance in Deep Ensembles

[1:45] From Coarse to Fine: Enable Comprehensive Graph Self-supervised Learning with Multi-granular Semantic Ensemble

[2:00] Decomposing Uncertainty for Large Language Models through Input Clarification Ensembling

[2:15] AlphaFold Meets Flow Matching for Generating Protein Ensembles

(ends 2:30 AM)

2:30 a.m.

Poster Session 5 [2:30-4:00]

Posters 2:30-4:00

Saliency strikes back: How filtering out high frequencies improves white-box explanations

PruNeRF: Segment-Centric Dataset Pruning via 3D Spatial Consistency

BAT: Learning to Reason about Spatial Sounds with Large Language Models

Inferring Change Points in High-Dimensional Linear Regression via Approximate Message Passing

Learning Surrogates for Offline Black-Box Optimization via Gradient Matching

Receptive Fields As Experts in Convolutional Neural Architectures

Dynamic Metric Embedding into lp Space

Position: Opportunities Exist for Machine Learning in Magnetic Fusion Energy

Agnostic Sample Compression Schemes for Regression

Verification of Machine Unlearning is Fragile

Fully-Dynamic Approximate Decision Trees With Worst-Case Update Time Guarantees

Stereo Risk: A Continuous Modeling Approach to Stereo Matching

Breaking the Barrier: Enhanced Utility and Robustness in Smoothed DRL Agents

Parameterized Physics-informed Neural Networks for Parameterized PDEs

PolySketchFormer: Fast Transformers via Sketching Polynomial Kernels

Best Arm Identification for Stochastic Rising Bandits

Causal Action Influence Aware Counterfactual Data Augmentation

Scalable and Flexible Causal Discovery with an Efficient Test for Adjacency

Standardized Interpretable Fairness Measures for Continuous Risk Scores

A Dynamical Model of Neural Scaling Laws

Transolver: A Fast Transformer Solver for PDEs on General Geometries

Look Ahead or Look Around? A Theoretical Comparison Between Autoregressive and Masked Pretraining

Stochastic Weakly Convex Optimization beyond Lipschitz Continuity

On The Fairness Impacts of Hardware Selection in Machine Learning

Decomposed Linear Dynamical Systems (dLDS) for learning the latent components of neural dynamics

Sample Average Approximation for Conditional Stochastic Optimization with Dependent Data

Unveiling the Potential of AI for Nanomaterial Morphology Prediction

The Pitfalls of Next-Token Prediction

A Fresh Take on Stale Embeddings: Improving Dense Retriever Training with Corrector Networks

StrWAEs to Invariant Representations

Interpreting Equivariant Representations

Configurable Mirror Descent: Towards a Unification of Decision Making

NDOT: Neuronal Dynamics-based Online Training for Spiking Neural Networks

Accelerating Convergence of Score-Based Diffusion Models, Provably

WARM: On the Benefits of Weight Averaged Reward Models

Noise-Aware Algorithm for Heterogeneous Differentially Private Federated Learning

Self-Driven Entropy Aggregation for Byzantine-Robust Heterogeneous Federated Learning

When Linear Attention Meets Autoregressive Decoding: Towards More Effective and Efficient Linearized Large Language Models

On Hypothesis Transfer Learning of Functional Linear Models

Understanding Forgetting in Continual Learning with Linear Regression

Autonomous Sparse Mean-CVaR Portfolio Optimization

Dual Operating Modes of In-Context Learning

Nonsmooth Implicit Differentiation: Deterministic and Stochastic Convergence Rates

Disguised Copyright Infringement of Latent Diffusion Models

Do Transformer World Models Give Better Policy Gradients?

A General Theory for Softmax Gating Multinomial Logistic Mixture of Experts

Floating Anchor Diffusion Model for Multi-motif Scaffolding

Momentum for the Win: Collaborative Federated Reinforcement Learning across Heterogeneous Environments

How Language Model Hallucinations Can Snowball

How Free is Parameter-Free Stochastic Optimization?

FRAPPÉ: A Group Fairness Framework for Post-Processing Everything

Incorporating Information into Shapley Values: Reweighting via a Maximum Entropy Approach

Energy-Guided Diffusion Sampling for Offline-to-Online Reinforcement Learning

C-RAG: Certified Generation Risks for Retrieval-Augmented Language Models

On the Identifiability of Switching Dynamical Systems

Refined Coreset Selection: Towards Minimal Coreset Size under Model Performance Constraints

CHEMREASONER: Heuristic Search over a Large Language Model’s Knowledge Space using Quantum-Chemical Feedback

Localizing Task Information for Improved Model Merging and Compression

BiSHop: Bi-Directional Cellular Learning for Tabular Data with Generalized Sparse Modern Hopfield Model

Differentiable Distributionally Robust Optimization Layers

MultiMax: Sparse and Multi-Modal Attention Learning

Accelerating Parallel Sampling of Diffusion Models

An Analysis of Linear Time Series Forecasting Models

Inferring Dynamic Networks from Marginals with Iterative Proportional Fitting

Privacy-Preserving Data Release Leveraging Optimal Transport and Particle Gradient Descent

Adaptive Hierarchical Certification for Segmentation using Randomized Smoothing

Converting Transformers to Polynomial Form for Secure Inference Over Homomorphic Encryption

LLM-Empowered State Representation for Reinforcement Learning

Learning Causal Domain-Invariant Temporal Dynamics for Few-Shot Action Recognition

eCeLLM: Generalizing Large Language Models for E-commerce from Large-scale, High-quality Instruction Data

Time Weaver: A Conditional Time Series Generation Model

Exploring Correlations of Self-Supervised Tasks for Graphs

Fast Peer Adaptation with Context-aware Exploration

On Convergence of Incremental Gradient for Non-convex Smooth Functions

Clifford-Steerable Convolutional Neural Networks

A Universal Transfer Theorem for Convex Optimization Algorithms Using Inexact First-order Oracles

Statistically Optimal Generative Modeling with Maximum Deviation from the Empirical Distribution

Correlation-Induced Label Prior for Semi-Supervised Multi-Label Learning

Test-Time Model Adaptation with Only Forward Passes

Cross-domain Open-world Discovery

A Study of First-Order Methods with a Deterministic Relative-Error Gradient Oracle

A General Framework for Learning from Weak Supervision

Category-Aware Active Domain Adaptation

Position: Social Choice Should Guide AI Alignment in Dealing with Diverse Human Feedback

ReLUs Are Sufficient for Learning Implicit Neural Representations

Re-Dock: Towards Flexible and Realistic Molecular Docking with Diffusion Bridge

Knowledge Distillation with Auxiliary Variable

AMPA: Adaptive Mixed Precision Allocation for Low-Bit Integer Training

Sparser, Better, Deeper, Stronger: Improving Static Sparse Training with Exact Orthogonal Initialization

Detecting Any instruction-to-answer interaction relationship:Universal Instruction-to-Answer Navigator for Med-VQA

Relaxing the Accurate Imputation Assumption in Doubly Robust Learning for Debiased Collaborative Filtering

Multiplicative Weights Update, Area Convexity and Random Coordinate Descent for Densest Subgraph Problems

Language Agent Tree Search Unifies Reasoning, Acting, and Planning in Language Models

Bias of Stochastic Gradient Descent or the Architecture: Disentangling the Effects of Overparameterization of Neural Networks

FedBAT: Communication-Efficient Federated Learning via Learnable Binarization

LESS: Selecting Influential Data for Targeted Instruction Tuning

Generalization Bounds for Causal Regression: Insights, Guarantees and Sensitivity Analysis

SpikeZIP-TF: Conversion is All You Need for Transformer-based SNN

Feedback Loops With Language Models Drive In-Context Reward Hacking

Agent-Specific Effects: A Causal Effect Propagation Analysis in Multi-Agent MDPs

Individualized Privacy Accounting via Subsampling with Applications in Combinatorial Optimization

Efficient Non-stationary Online Learning by Wavelets with Applications to Online Distribution Shift Adaptation

Spotting LLMs With Binoculars: Zero-Shot Detection of Machine-Generated Text

A Federated Stochastic Multi-level Compositional Minimax Algorithm for Deep AUC Maximization

Differentially Private Post-Processing for Fair Regression

RL-CFR: Improving Action Abstraction for Imperfect Information Extensive-Form Games with Reinforcement Learning

EvIL: Evolution Strategies for Generalisable Imitation Learning

Policy Learning for Balancing Short-Term and Long-Term Rewards

Position: Relational Deep Learning - Graph Representation Learning on Relational Databases

Vocabulary for Universal Approximation: A Linguistic Perspective of Mapping Compositions

ACM-MILP: Adaptive Constraint Modification via Grouping and Selection for Hardness-Preserving MILP Instance Generation

Geometry-Aware Instrumental Variable Regression

DRED: Zero-Shot Transfer in Reinforcement Learning via Data-Regularised Environment Design

Exploring the Benefit of Activation Sparsity in Pre-training

Theoretical Analysis of Learned Database Operations under Distribution Shift through Distribution Learnability

RMIB: Representation Matching Information Bottleneck for Matching Text Representations

Make-A-Shape: a Ten-Million-scale 3D Shape Model

Unsupervised Episode Generation for Graph Meta-learning

The Balanced-Pairwise-Affinities Feature Transform

PRISE: LLM-Style Sequence Compression for Learning Temporal Action Abstractions in Control

Advancing Dynamic Sparse Training by Exploring Optimization Opportunities

KV-Runahead: Scalable Causal LLM Inference by Parallel Key-Value Cache Generation

Agnostic Interactive Imitation Learning: New Theory and Practical Algorithms

Semantic-Aware Human Object Interaction Image Generation

Out-of-Distribution Detection via Deep Multi-Comprehension Ensemble

SPHINX-X: Scaling Data and Parameters for a Family of Multi-modal Large Language Models

Revisiting the Role of Language Priors in Vision-Language Models

Data-efficient Large Vision Models through Sequential Autoregression

Pedestrian Attribute Recognition as Label-balanced Multi-label Learning

Bayesian Adaptation of Network Depth and Width for Continual Learning

Towards Generalization beyond Pointwise Learning: A Unified Information-theoretic Perspective

Emergent Equivariance in Deep Ensembles

Is Epistemic Uncertainty Faithfully Represented by Evidential Deep Learning Methods?

Position: Social Environment Design Should be Further Developed for AI-based Policy-Making

Memory-Space Visual Prompting for Efficient Vision-Language Fine-Tuning

Safe and Robust Subgame Exploitation in Imperfect Information Games

A Dual-module Framework for Counterfactual Estimation over Time

S$\Omega$I: Score-based O-INFORMATION Estimation

Learning to Reach Goals via Diffusion

PARDEN, Can You Repeat That? Defending against Jailbreaks via Repetition

Robust Sparse Estimation for Gaussians with Optimal Error under Huber Contamination

Neural Operators with Localized Integral and Differential Kernels

Fast Co-Training under Weak Dependence via Stream-Based Active Learning

Tripod: Three Complementary Inductive Biases for Disentangled Representation Learning

A Contextual Combinatorial Bandit Approach to Negotiation

Get More with LESS: Synthesizing Recurrence with KV Cache Compression for Efficient LLM Inference

Layer-Aware Analysis of Catastrophic Overfitting: Revealing the Pseudo-Robust Shortcut Dependency

Task-aware Orthogonal Sparse Network for Exploring Shared Knowledge in Continual Learning

Homomorphism Counts for Graph Neural Networks: All About That Basis

Accelerated Algorithms for Constrained Nonconvex-Nonconcave Min-Max Optimization and Comonotone Inclusion

Discovering Environments with XRM

Coprocessor Actor Critic: A Model-Based Reinforcement Learning Approach For Adaptive Brain Stimulation

Reprompting: Automated Chain-of-Thought Prompt Inference Through Gibbs Sampling

Toward Availability Attacks in 3D Point Clouds

A Global Geometric Analysis of Maximal Coding Rate Reduction

Multigroup Robustness

Near-Linear Time Approximation Algorithms for k-means with Outliers

From Coarse to Fine: Enable Comprehensive Graph Self-supervised Learning with Multi-granular Semantic Ensemble

Causal Discovery via Conditional Independence Testing with Proxy Variables

On the Embedding Collapse when Scaling up Recommendation Models

Coarse-To-Fine Tensor Trains for Compact Visual Representations

Skill Set Optimization: Reinforcing Language Model Behavior via Transferable Skills

PIPER: Primitive-Informed Preference-based Hierarchical Reinforcement Learning via Hindsight Relabeling

Federated Offline Reinforcement Learning: Collaborative Single-Policy Coverage Suffices

On the Generalization of Equivariant Graph Neural Networks

Offline-Boosted Actor-Critic: Adaptively Blending Optimal Historical Behaviors in Deep Off-Policy RL

Mastering Zero-Shot Interactions in Cooperative and Competitive Simultaneous Games

Sample-Efficient Robust Multi-Agent Reinforcement Learning in the Face of Environmental Uncertainty

RoboDreamer: Learning Compositional World Models for Robot Imagination

Convergence Guarantees for the DeepWalk Embedding on Block Models

Connecting the Dots: Collaborative Fine-tuning for Black-Box Vision-Language Models

An LLM Compiler for Parallel Function Calling

ALERT-Transformer: Bridging Asynchronous and Synchronous Machine Learning for Real-Time Event-based Spatio-Temporal Data

Graph External Attention Enhanced Transformer

Counterfactual Metarules for Local and Global Recourse

Reward-Free Kernel-Based Reinforcement Learning

Generalized Sobolev Transport for Probability Measures on a Graph

Sharp Rates in Dependent Learning Theory: Avoiding Sample Size Deflation for the Square Loss

Iterative Preference Learning from Human Feedback: Bridging Theory and Practice for RLHF under KL-constraint

Knowledge Transfer from Vision Foundation Models for Efficient Training of Small Task-specific Models

Position: The Reasonable Person Standard for AI

Towards AutoAI: Optimizing a Machine Learning System with Black-box and Differentiable Components

Simulation of Graph Algorithms with Looped Transformers

Fair Data Representation for Machine Learning at the Pareto Frontier

Variational Linearized Laplace Approximation for Bayesian Deep Learning

Position: Insights from Survey Methodology can Improve Training Data

Liouville Flow Importance Sampler

X-Oscar: A Progressive Framework for High-quality Text-guided 3D Animatable Avatar Generation

Improved Bounds for Pure Private Agnostic Learning: Item-Level and User-Level Privacy

Stochastic Localization via Iterative Posterior Sampling

Layerwise Proximal Replay: A Proximal Point Method for Online Continual Learning

Revealing the Dark Secrets of Extremely Large Kernel ConvNets on Robustness

DiNADO: Norm-Disentangled Neurally-Decomposed Oracles for Controlling Language Models

Contrastive Predict-and-Search for Mixed Integer Linear Programs

Position: Towards Implicit Prompt For Text-To-Image Models

Counterfactual Reasoning for Multi-Label Image Classification via Patching-Based Training

Prior Specification for Bayesian Matrix Factorization via Prior Predictive Matching

Universality of Linear Recurrences Followed by Non-linear Projections: Finite-Width Guarantees and Benefits of Complex Eigenvalues

Sequence Compression Speeds Up Credit Assignment in Reinforcement Learning

Adversarially Robust Deep Multi-View Clustering: A Novel Attack and Defense Framework

Mimicking Better by Matching the Approximate Action Distribution

How to Explore with Belief: State Entropy Maximization in POMDPs

Optimal Transport for Structure Learning Under Missing Data

Bridging discrete and continuous state spaces: Exploring the Ehrenfest process in time-continuous diffusion models

Knowledge Graphs Can be Learned with Just Intersection Features

Reward Shaping for Reinforcement Learning with An Assistant Reward Agent

HarmoDT: Harmony Multi-Task Decision Transformer for Offline Reinforcement Learning

InferCept: Efficient Intercept Support for Augmented Large Language Model Inference

What is the Long-Run Distribution of Stochastic Gradient Descent? A Large Deviations Analysis

Optimal Differentially Private Model Training with Public Data

Relational Learning in Pre-Trained Models: A Theory from Hypergraph Recovery Perspective

Position: Rethinking Post-Hoc Search-Based Neural Approaches for Solving Large-Scale Traveling Salesman Problems

The Good, The Bad, and Why: Unveiling Emotions in Generative AI

OTMatch: Improving Semi-Supervised Learning with Optimal Transport

UPAM: Unified Prompt Attack in Text-to-Image Generation Models Against Both Textual Filters and Visual Checkers

Rethinking Guidance Information to Utilize Unlabeled Samples: A Label Encoding Perspective

Predictive Linear Online Tracking for Unknown Targets

Bootstrapping Fisher Market Equilibrium and First-Price Pacing Equilibrium

Rethinking Transformers in Solving POMDPs

Shifted Interpolation for Differential Privacy

Robust Classification via a Single Diffusion Model

Variational Inference with Coverage Guarantees in Simulation-Based Inference

Empowering Graph Invariance Learning with Deep Spurious Infomax

LCA-on-the-Line: Benchmarking Out of Distribution Generalization with Class Taxonomies

Understanding Stochastic Natural Gradient Variational Inference

Subgraphormer: Unifying Subgraph GNNs and Graph Transformers via Graph Products

Position: A Call to Action for a Human-Centered AutoML Paradigm

FedBPT: Efficient Federated Black-box Prompt Tuning for Large Language Models

Online Speculative Decoding

COALA: A Practical and Vision-Centric Federated Learning Platform

Exploring the Complexity of Deep Neural Networks through Functional Equivalence

Correcting Diffusion-Based Perceptual Image Compression with Privileged End-to-End Decoder

Optimally Improving Cooperative Learning in a Social Setting

Fair Resource Allocation in Multi-Task Learning

AdsorbDiff: Adsorbate Placement via Conditional Denoising Diffusion

Information Complexity of Stochastic Convex Optimization: Applications to Generalization, Memorization, and Tracing

The Max-Min Formulation of Multi-Objective Reinforcement Learning: From Theory to a Model-Free Algorithm

Towards Robust Model-Based Reinforcement Learning Against Adversarial Corruption

Beyond Regular Grids: Fourier-Based Neural Operators on Arbitrary Domains

On the Last-Iterate Convergence of Shuffling Gradient Methods

Feature Reuse and Scaling: Understanding Transfer Learning with Protein Language Models

Explaining Graph Neural Networks via Structure-aware Interaction Index

Superpoint Gaussian Splatting for Real-Time High-Fidelity Dynamic Scene Reconstruction

Do Efficient Transformers Really Save Computation?

LoRAP: Transformer Sub-Layers Deserve Differentiated Structured Compression for Large Language Models

Online conformal prediction with decaying step sizes

Learning High-Order Relationships of Brain Regions

Domain-wise Data Acquisition to Improve Performance under Distribution Shift

Latent variable model for high-dimensional point process with structured missingness

Improving Equivariant Graph Neural Networks on Large Geometric Graphs via Virtual Nodes Learning

Domain Generalisation via Imprecise Learning

MFTN: A Multi-scale Feature Transfer Network Based on IMatchFormer for Hyperspectral Image Super-Resolution

Clustered Federated Learning via Gradient-based Partitioning

Revisiting Character-level Adversarial Attacks for Language Models

Reinformer: Max-Return Sequence Modeling for Offline RL

Adaptive Sampling of k-Space in Magnetic Resonance for Rapid Pathology Prediction

Learning in Feature Spaces via Coupled Covariances: Asymmetric Kernel SVD and Nyström method

Locality-Sensitive Hashing-Based Efficient Point Transformer with Applications in High-Energy Physics

Causal-IQA: Towards the Generalization of Image Quality Assessment Based on Causal Inference

BiLLM: Pushing the Limit of Post-Training Quantization for LLMs

Roping in Uncertainty: Robustness and Regularization in Markov Games

Complexity Matters: Feature Learning in the Presence of Spurious Correlations

New Bounds on the Cohesion of Complete-link and Other Linkage Methods for Agglomerative Clustering

Precise Accuracy / Robustness Tradeoffs in Regression: Case of General Norms

Language-guided Skill Learning with Temporal Variational Inference

Chain-of-Thought Predictive Control

Learning Shadow Variable Representation for Treatment Effect Estimation under Collider Bias

Provable Risk-Sensitive Distributional Reinforcement Learning with General Function Approximation

diff History for Neural Language Agents

Expert Proximity as Surrogate Rewards for Single Demonstration Imitation Learning

Linguistic Calibration of Long-Form Generations

Outlier-aware Slicing for Post-Training Quantization in Vision Transformer

Generative Modeling on Manifolds Through Mixture of Riemannian Diffusion Processes

Second-Order Uncertainty Quantification: A Distance-Based Approach

SPABA: A Single-Loop and Probabilistic Stochastic Bilevel Algorithm Achieving Optimal Sample Complexity

Revisit the Essence of Distilling Knowledge through Calibration

Locally Interdependent Multi-Agent MDP: Theoretical Framework for Decentralized Agents with Dynamic Dependencies

Convex Relaxations of ReLU Neural Networks Approximate Global Optima in Polynomial Time

CuTS: Customizable Tabular Synthetic Data Generation

Kernel-Based Evaluation of Conditional Biological Sequence Models

Mechanistic Neural Networks for Scientific Machine Learning

Stochastic Bandits with ReLU Neural Networks

A Provable Decision Rule for Out-of-Distribution Detection

Stationarity without mean reversion in improper Gaussian processes

Slicedit: Zero-Shot Video Editing With Text-to-Image Diffusion Models Using Spatio-Temporal Slices

Grokking Group Multiplication with Cosets

ESM All-Atom: Multi-Scale Protein Language Model for Unified Molecular Modeling

Online Variational Sequential Monte Carlo

RICE: Breaking Through the Training Bottlenecks of Reinforcement Learning with Explanation

Large Language Models are Geographically Biased

High-Probability Convergence for Composite and Distributed Stochastic Minimization and Variational Inequalities with Heavy-Tailed Noise

Feel-Good Thompson Sampling for Contextual Dueling Bandits

Improving fine-grained understanding in image-text pre-training

Temporal Spiking Neural Networks with Synaptic Delay for Graph Reasoning

Seizing Serendipity: Exploiting the Value of Past Success in Off-Policy Actor-Critic

Generative Marginalization Models

Robust Learning-Augmented Dictionaries

Memoria: Resolving Fateful Forgetting Problem through Human-Inspired Memory Architecture

Lessons from Generalization Error Analysis of Federated Learning: You May Communicate Less Often!

Symmetric Replay Training: Enhancing Sample Efficiency in Deep Reinforcement Learning for Combinatorial Optimization

Learning with Partial-Label and Unlabeled Data: A Uniform Treatment for Supervision Redundancy and Insufficiency

Differentially Private Worst-group Risk Minimization

Single-Model Attribution of Generative Models Through Final-Layer Inversion

Low-Rank Similarity Mining for Multimodal Dataset Distillation

Smooth Tchebycheff Scalarization for Multi-Objective Optimization

Zero-Shot Unsupervised and Text-Based Audio Editing Using DDPM Inversion

DiffStitch: Boosting Offline Reinforcement Learning with Diffusion-based Trajectory Stitching

Unifying Bayesian Flow Networks and Diffusion Models through Stochastic Differential Equations

VideoPrism: A Foundational Visual Encoder for Video Understanding

An amortized approach to non-linear mixed-effects modeling based on neural posterior estimation

Auto-Linear Phenomenon in Subsurface Imaging

Individual Contributions as Intrinsic Exploration Scaffolds for Multi-agent Reinforcement Learning

The Expressive Power of Path-Based Graph Neural Networks

SPADE: Sparsity-Guided Debugging for Deep Neural Networks

Deep Neural Room Acoustics Primitive

How Flawed Is ECE? An Analysis via Logit Smoothing

On The Complexity of First-Order Methods in Stochastic Bilevel Optimization

Safe Exploration in Dose Finding Clinical Trials with Heterogeneous Participants

Challenges in Training PINNs: A Loss Landscape Perspective

Monotone, Bi-Lipschitz, and Polyak-Łojasiewicz Networks

EMC$^2$: Efficient MCMC Negative Sampling for Contrastive Learning with Global Convergence

Graph Neural PDE Solvers with Conservation and Similarity-Equivariance

Can Machines Learn the True Probabilities?

Adversarial Attacks on Combinatorial Multi-Armed Bandits

The Privacy Power of Correlated Noise in Decentralized Learning

Practical Performance Guarantees for Pipelined DNN Inference

Caduceus: Bi-Directional Equivariant Long-Range DNA Sequence Modeling

Position: Compositional Generative Modeling: A Single Model is Not All You Need

Split-Ensemble: Efficient OOD-aware Ensemble via Task and Model Splitting

S3GCL: Spectral, Swift, Spatial Graph Contrastive Learning

Post-hoc Part-Prototype Networks

Few-shot Adaptation to Distribution Shifts By Mixing Source and Target Embeddings

Rotational Equilibrium: How Weight Decay Balances Learning Across Neural Networks

Private Vector Mean Estimation in the Shuffle Model: Optimal Rates Require Many Messages

Defense against Backdoor Attack on Pre-trained Language Models via Head Pruning and Attention Normalization

Neural Tangent Kernels for Axis-Aligned Tree Ensembles

Hybrid Neural Representations for Spherical Data

Don't trust your eyes: on the (un)reliability of feature visualizations

Subhomogeneous Deep Equilibrium Models

Finite Volume Features, Global Geometry Representations, and Residual Training for Deep Learning-based CFD Simulation

OSN: Infinite Representations of Dynamic 3D Scenes from Monocular Videos

Sliced-Wasserstein Estimation with Spherical Harmonics as Control Variates

Prompt-tuning Latent Diffusion Models for Inverse Problems

Triplet Interaction Improves Graph Transformers: Accurate Molecular Graph Learning with Triplet Graph Transformers

A Statistical Theory of Regularization-Based Continual Learning

On the Trajectory Regularity of ODE-based Diffusion Sampling

Critical feature learning in deep neural networks

A Neural-Guided Dynamic Symbolic Network for Exploring Mathematical Expressions from Data

Why Larger Language Models Do In-context Learning Differently?

Context-Guided Diffusion for Out-of-Distribution Molecular and Protein Design

Assessing Large Language Models on Climate Information

A New Linear Scaling Rule for Private Adaptive Hyperparameter Optimization

Leverage Class-Specific Accuracy to Guide Data Generation for Improving Image Classification

Survival Kernets: Scalable and Interpretable Deep Kernel Survival Analysis with an Accuracy Guarantee

Quantum Positional Encodings for Graph Neural Networks

DUPLEX: Dual GAT for Complex Embedding of Directed Graphs

Vague Prototype-Oriented Diffusion Model for Multi-Class Anomaly Detection

Path-Guided Particle-based Sampling

Sample-specific Masks for Visual Reprogramming-based Prompting

CasCast: Skillful High-resolution Precipitation Nowcasting via Cascaded Modelling

A Dynamic Algorithm for Weighted Submodular Cover Problem

Kernel Debiased Plug-in Estimation: Simultaneous, Automated Debiasing without Influence Functions for Many Target Parameters

Decomposing Uncertainty for Large Language Models through Input Clarification Ensembling

Learning Scale-Aware Spatio-temporal Implicit Representation for Event-based Motion Deblurring

REST: Efficient and Accelerated EEG Seizure Analysis through Residual State Updates

A Probabilistic Approach to Learning the Degree of Equivariance in Steerable CNNs

Equilibrium of Data Markets with Externality

Light and Optimal Schrödinger Bridge Matching

Latent Logic Tree Extraction for Event Sequence Explanation from LLMs

Prospector Heads: Generalized Feature Attribution for Large Models & Data

From Yes-Men to Truth-Tellers: Addressing Sycophancy in Large Language Models with Pinpoint Tuning

Learning Latent Structures in Network Games via Data-Dependent Gated-Prior Graph Variational Autoencoders

In-Context Unlearning: Language Models as Few-Shot Unlearners

Active Label Correction for Semantic Segmentation with Foundation Models

Improving Diffusion Models for Inverse Problems Using Optimal Posterior Covariance

Unlocking the Power of Spatial and Temporal Information in Medical Multimodal Pre-training

Differentiable Annealed Importance Sampling Minimizes The Jensen-Shannon Divergence Between Initial and Target Distribution

Retrieval-Augmented Score Distillation for Text-to-3D Generation

Structured Inverse-Free Natural Gradient Descent: Memory-Efficient & Numerically-Stable KFAC

Q-value Regularized Transformer for Offline Reinforcement Learning

SHINE: Shielding Backdoors in Deep Reinforcement Learning

Transferring Knowledge From Large Foundation Models to Small Downstream Models

InfiAgent-DABench: Evaluating Agents on Data Analysis Tasks

Copula-Nested Spectral Kernel Network

Generalization Error of Graph Neural Networks in the Mean-field Regime

Consistent Long-Term Forecasting of Ergodic Dynamical Systems

Unraveling the Impact of Heterophilic Structures on Graph Positive-Unlabeled Learning

Profile Reconstruction from Private Sketches

Causally Motivated Personalized Federated Invariant Learning with Shortcut-Averse Information-Theoretic Regularization

Double Variance Reduction: A Smoothing Trick for Composite Optimization Problems without First-Order Gradient

Equivariance via Minimal Frame Averaging for More Symmetries and Efficiency

Degeneration-free Policy Optimization: RL Fine-Tuning for Language Models without Degeneration

Quantum Algorithm for Online Exp-concave Optimization

Benchmarking Deletion Metrics with the Principled Explanations

Why Do Animals Need Shaping? A Theory of Task Composition and Curriculum Learning

Beyond Point Prediction: Score Matching-based Pseudolikelihood Estimation of Neural Marked Spatio-Temporal Point Process

Neuro-Visualizer: A Novel Auto-Encoder-Based Loss Landscape Visualization Method With an Application in Knowledge-Guided Machine Learning

Harnessing Neural Unit Dynamics for Effective and Scalable Class-Incremental Learning

Self-Composing Policies for Scalable Continual Reinforcement Learning

Decouple then Classify: A Dynamic Multi-view Labeling Strategy with Shared and Specific Information

Active Ranking and Matchmaking, with Perfect Matchings

Vector Quantization Pretraining for EEG Time Series with Random Projection and Phase Alignment

On the Independence Assumption in Neurosymbolic Learning

Infinite-Horizon Distributionally Robust Regret-Optimal Control

Viewing Transformers Through the Lens of Long Convolutions Layers

Proactive Detection of Voice Cloning with Localized Watermarking

Evolution of Heuristics: Towards Efficient Automatic Algorithm Design Using Large Language Model

Accelerating Heterogeneous Federated Learning with Closed-form Classifiers

Single-Trajectory Distributionally Robust Reinforcement Learning

EquiAV: Leveraging Equivariance for Audio-Visual Contrastive Learning

Verifying message-passing neural networks via topology-based bounds tightening

AnyTool: Self-Reflective, Hierarchical Agents for Large-Scale API Calls

Distilling Morphology-Conditioned Hypernetworks for Efficient Universal Morphology Control

RLVF: Learning from Verbal Feedback without Overgeneralization

Parallelized Spatiotemporal Slot Binding for Videos

Graph Neural Networks Use Graphs When They Shouldn't

Probabilistic Forecasting with Stochastic Interpolants and Föllmer Processes

Batch and match: black-box variational inference with a score-based divergence

Improving SAM Requires Rethinking its Optimization Formulation

(ends 4:00 AM)

3:30 a.m.

Break:

Hosted Lunch

(ends 5:00 AM)

4:30 a.m.

Poster Session 6 [4:30-6:00]

Posters 4:30-6:00

Autoformalizing Euclidean Geometry

Graph-based Time Series Clustering for End-to-End Hierarchical Forecasting

Universal Gradient Methods for Stochastic Convex Optimization

StrokeNUWA—Tokenizing Strokes for Vector Graphic Synthesis

The WMDP Benchmark: Measuring and Reducing Malicious Use with Unlearning

Can Gaussian Sketching Converge Faster on a Preconditioned Landscape?

LoCoCo: Dropping In Convolutions for Long Context Compression

Evaluation of Trajectory Distribution Predictions with Energy Score

Do Topological Characteristics Help in Knowledge Distillation?

EE-LLM: Large-Scale Training and Inference of Early-Exit Large Language Models with 3D Parallelism

SFC: Achieve Accurate Fast Convolution under Low-precision Arithmetic

Partial Multi-View Multi-Label Classification via Semantic Invariance Learning and Prototype Modeling

Integrating Global Context Contrast and Local Sensitivity for Blind Image Quality Assessment

Environment Design for Inverse Reinforcement Learning

ULAREF: A Unified Label Refinement Framework for Learning with Inaccurate Supervision

End-to-End Neuro-Symbolic Reinforcement Learning with Textual Explanations

Minimizing $f$-Divergences by Interpolating Velocity Fields

Joint Composite Latent Space Bayesian Optimization

Scalable AI Safety via Doubly-Efficient Debate

Graph Structure Extrapolation for Out-of-Distribution Generalization

PAC-Bayesian Error Bound, via Rényi Divergence, for a Class of Linear Time-Invariant State-Space Models

Zero-Shot Reinforcement Learning via Function Encoders

Prediction-powered Generalization of Causal Inferences

DéjàVu: KV-cache Streaming for Fast, Fault-tolerant Generative LLM Serving

Leveraging VLM-Based Pipelines to Annotate 3D Objects

DataFreeShield: Defending Adversarial Attacks without Training Data

FedMBridge: Bridgeable Multimodal Federated Learning

How to Leverage Diverse Demonstrations in Offline Imitation Learning

Towards Optimal Adversarial Robust Q-learning with Bellman Infinity-error

Recovering Labels from Local Updates in Federated Learning

PairNet: Training with Observed Pairs to Estimate Individual Treatment Effect

ATraDiff: Accelerating Online Reinforcement Learning with Imaginary Trajectories

Fourier Controller Networks for Real-Time Decision-Making in Embodied Learning

FightLadder: A Benchmark for Competitive Multi-Agent Reinforcement Learning

HGCN2SP: Hierarchical Graph Convolutional Network for Two-Stage Stochastic Programming

Model Assessment and Selection under Temporal Distribution Shift

MVMoE: Multi-Task Vehicle Routing Solver with Mixture-of-Experts

Statistical Properties of Robust Satisficing

How Graph Neural Networks Learn: Lessons from Training Dynamics

On the sample complexity of conditional independence testing with Von Mises estimator with application to causal discovery

Contrastive Learning for Clinical Outcome Prediction with Partial Data Sources

Scaling Beyond the GPU Memory Limit for Large Mixture-of-Experts Model Training

Random Scaling and Momentum for Non-smooth Non-convex Optimization

Task Groupings Regularization: Data-Free Meta-Learning with Heterogeneous Pre-trained Models

Low-Rank Bandits via Tight Two-to-Infinity Singular Subspace Recovery

Predicting Lagrangian Multipliers for Mixed Integer Linear Programs

Vectorized Conditional Neural Fields: A Framework for Solving Time-dependent Parametric Partial Differential Equations

Irregular Multivariate Time Series Forecasting: A Transformable Patching Graph Neural Networks Approach

Boosting Reinforcement Learning with Strongly Delayed Feedback Through Auxiliary Short Delays

Provable Representation with Efficient Planning for Partially Observable Reinforcement Learning

Prior Mismatch and Adaptation in PnP-ADMM with a Nonconvex Convergence Analysis

DPN: Decoupling Partition and Navigation for Neural Solvers of Min-max Vehicle Routing Problems

Dynamic Memory Compression: Retrofitting LLMs for Accelerated Inference

Spider: A Unified Framework for Context-dependent Concept Segmentation

Learning the Uncertainty Sets of Linear Control Systems via Set Membership: A Non-asymptotic Analysis

Harnessing the Power of Neural Operators with Automatically Encoded Conservation Laws

Understanding Diffusion Models by Feynman's Path Integral

Best of Both Worlds Guarantees for Smoothed Online Quadratic Optimization

Structure-Aware E(3)-Invariant Molecular Conformer Aggregation Networks

Wukong: Towards a Scaling Law for Large-Scale Recommendation

Adaptive Proximal Gradient Methods Are Universal Without Approximation

ED-Copilot: Reduce Emergency Department Wait Time with Language Model Diagnostic Assistance

Sequential Asynchronous Action Coordination in Multi-Agent Systems: A Stackelberg Decision Transformer Approach

A Unified Recipe for Deriving (Time-Uniform) PAC-Bayes Bounds

On Positivity Condition for Causal Inference

QORA: Zero-Shot Transfer via Interpretable Object-Relational Model Learning

Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models

From Self-Attention to Markov Models: Unveiling the Dynamics of Generative Transformers

On Universally Optimal Algorithms for A/B Testing

Bring Your Own (Non-Robust) Algorithm to Solve Robust MDPs by Estimating The Worst Kernel

Feature Importance Disparities for Data Bias Investigations

Neural Image Compression with Text-guided Encoding for both Pixel-level and Perceptual Fidelity

Unifying Image Processing as Visual Prompting Question Answering

Deep Equilibrium Models are Almost Equivalent to Not-so-deep Explicit Models for High-dimensional Gaussian Mixtures

How Does Goal Relabeling Improve Sample Efficiency?

MLI Formula: A Nearly Scale-Invariant Solution with Noise Perturbation

Why Do You Grok? A Theoretical Analysis on Grokking Modular Addition

Position: Scarce Resource Allocations That Rely On Machine Learning Should Be Randomized

Physics-Informed Neural Network Policy Iteration: Algorithms, Convergence, and Verification

Neural Collapse for Cross-entropy Class-Imbalanced Learning with Unconstrained ReLU Features Model

Adapt and Diffuse: Sample-adaptive Reconstruction via Latent Diffusion Models

Q-Probe: A Lightweight Approach to Reward Maximization for Language Models

Privacy Preserving Adaptive Experiment Design

Emergent Representations of Program Semantics in Language Models Trained on Programs

A Tale of Tails: Model Collapse as a Change of Scaling Laws

Easing Concept Bleeding in Diffusion via Entity Localization and Anchoring

Deciphering RNA Secondary Structure Prediction: A Probabilistic K-Rook Matching Perspective

Slow and Steady Wins the Race: Maintaining Plasticity with Hare and Tortoise Networks

Hieros: Hierarchical Imagination on Structured State Space Sequence World Models

Accelerating Transformer Pre-training with 2:4 Sparsity

Residual Quantization with Implicit Neural Codebooks

Conformal Prediction with Learned Features

Model-Based RL for Mean-Field Games is not Statistically Harder than Single-Agent RL

Privacy Attacks in Decentralized Learning

Adaptive Robust Learning using Latent Bernoulli Variables

Early Time Classification with Accumulated Accuracy Gap Control

Evaluating Instrument Validity using the Principle of Independent Mechanisms

Mitigating Privacy Risk in Membership Inference by Convex-Concave Loss

Estimating Distributional Treatment Effects in Randomized Experiments: Machine Learning for Variance Reduction

Generalizing Knowledge Graph Embedding with Universal Orthogonal Parameterization

Sign Gradient Descent-based Neuronal Dynamics: ANN-to-SNN Conversion Beyond ReLU Network

RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback

Fast and Sample Efficient Multi-Task Representation Learning in Stochastic Contextual Bandits

Tuning-Free Stochastic Optimization

Sliced Wasserstein with Random-Path Projecting Directions

A Single-Loop Robust Policy Gradient Method for Robust Markov Decision Processes

Foundations of Testing for Finite-Sample Causal Discovery

Translating Subgraphs to Nodes Makes Simple GNNs Strong and Efficient for Subgraph Representation Learning

DE-COP: Detecting Copyrighted Content in Language Models Training Data

Graph Neural Network Explanations are Fragile

Cascade-CLIP: Cascaded Vision-Language Embeddings Alignment for Zero-Shot Semantic Segmentation

When is Transfer Learning Possible?

Consistent Adversarially Robust Linear Classification: Non-Parametric Setting

A Dense Reward View on Aligning Text-to-Image Diffusion with Preference

Sample as you Infer: Predictive Coding with Langevin Dynamics

Binary Decomposition: A Problem Transformation Perspective for Open-Set Semi-Supervised Learning

DisCo-Diff: Enhancing Continuous Diffusion Models with Discrete Latents

Diffusion Models Encode the Intrinsic Dimension of Data Manifolds

Pursuing Overall Welfare in Federated Learning through Sequential Decision Making

On the Complexity of Finite-Sum Smooth Optimization under the Polyak–Łojasiewicz Condition

Langevin Policy for Safe Reinforcement Learning

Parameter Estimation in DAGs from Incomplete Data via Optimal Transport

Sequential Disentanglement by Extracting Static Information From A Single Sequence Element

Generative Active Learning for Long-tailed Instance Segmentation

Subequivariant Reinforcement Learning in 3D Multi-Entity Physical Environments

Multi-Track Message Passing: Tackling Oversmoothing and Oversquashing in Graph Learning via Preventing Heterophily Mixing

Mitigating Label Noise on Graphs via Topological Sample Selection

Position: Reinforcement Learning in Dynamic Treatment Regimes Needs Critical Reexamination

Automated Loss function Search for Class-imbalanced Node Classification

Safe Reinforcement Learning using Finite-Horizon Gradient-based Estimation

Causality Based Front-door Defense Against Backdoor Attack on Language Models

Accelerated Speculative Sampling Based on Tree Monte Carlo

Self-cognitive Denoising in the Presence of Multiple Noisy Label Sources

LaMAGIC: Language-Model-based Topology Generation for Analog Integrated Circuits

Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs

Disentangled Graph Self-supervised Learning for Out-of-Distribution Generalization

Why do Variational Autoencoders Really Promote Disentanglement?

Sparse and Structured Hopfield Networks

On the Expressive Power of Spectral Invariant Graph Neural Networks

ReconBoost: Boosting Can Achieve Modality Reconcilement

Sparse-to-dense Multimodal Image Registration via Multi-Task Learning

Neuro-Symbolic Temporal Point Processes

Risk Aware Benchmarking of Large Language Models

NExT-GPT: Any-to-Any Multimodal LLM

Graph Out-of-Distribution Detection Goes Neighborhood Shaping

Learning Latent Space Hierarchical EBM Diffusion Models

FedCal: Achieving Local and Global Calibration in Federated Learning via Aggregated Parameterized Scaler

Stochastic Optimization with Arbitrary Recurrent Data Sampling

Navigating Complexity: Toward Lossless Graph Condensation via Expanding Window Matching

Position: Open-Endedness is Essential for Artificial Superhuman Intelligence

Parameter Efficient Quasi-Orthogonal Fine-Tuning via Givens Rotation

Critical windows: non-asymptotic theory for feature emergence in diffusion models

On the Hardness of Probabilistic Neurosymbolic Learning

Improving Neural Logic Machines via Failure Reflection

Enhancing Storage and Computational Efficiency in Federated Multimodal Learning for Large-Scale Models

MindEye2: Shared-Subject Models Enable fMRI-To-Image With 1 Hour of Data

LAGMA: LAtent Goal-guided Multi-Agent Reinforcement Learning

GFlowNet Training by Policy Gradients

PAGER: Accurate Failure Characterization in Deep Regression Models

QuRating: Selecting High-Quality Data for Training Language Models

Pre-Training Protein Bi-level Representation Through Span Mask Strategy On 3D Protein Chains

AttNS: Attention-Inspired Numerical Solving For Limited Data Scenarios

Beyond the ROC Curve: Classification Trees Using Cost-Optimal Curves, with Application to Imbalanced Datasets

High-Dimensional Geometric Streaming for Nearly Low Rank Data

Bivariate Causal Discovery using Bayesian Model Selection

CRUXEval: A Benchmark for Code Reasoning, Understanding and Execution

Adaptive-Gradient Policy Optimization: Enhancing Policy Learning in Non-Smooth Differentiable Simulations

Inexact Newton-type Methods for Optimisation with Nonnegativity Constraints

A Subquadratic Time Algorithm for Robust Sparse Mean Estimation

Simplicity Bias of Two-Layer Networks beyond Linearly Separable Data

HALC: Object Hallucination Reduction via Adaptive Focal-Contrast Decoding

CosPGD: an efficient white-box adversarial attack for pixel-wise prediction tasks

MH-pFLID: Model Heterogeneous personalized Federated Learning via Injection and Distillation for Medical Data Analysis

Image Fusion via Vision-Language Model

Mean Field Langevin Actor-Critic: Faster Convergence and Global Optimality beyond Lazy Learning

Efficient Contrastive Learning for Fast and Accurate Inference on Graphs

Eureka-Moments in Transformers: Multi-Step Tasks Reveal Softmax Induced Optimization Problems

Novel Spectral Algorithms for the Partial Credit Model

CARTE: Pretraining and Transfer for Tabular Learning

Gradual Divergence for Seamless Adaptation: A Novel Domain Incremental Learning Method

Exploiting Human-AI Dependence for Learning to Defer

Adaptive Stabilization Based on Machine Learning for Column Generation

Principled Penalty-based Methods for Bilevel Reinforcement Learning and RLHF

Adaptive Online Experimental Design for Causal Discovery

NeWRF: A Deep Learning Framework for Wireless Radiation Field Reconstruction and Channel Prediction

Towards Efficient Exact Optimization of Language Model Alignment

How do Transformers Perform In-Context Autoregressive Learning ?

Improving Sample Efficiency of Model-Free Algorithms for Zero-Sum Markov Games

Model-Based Minimum Bayes Risk Decoding for Text Generation

COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability

CaM: Cache Merging for Memory-efficient LLMs Inference

$f$-Divergence Based Classification: Beyond the Use of Cross-Entropy

Conformalized Adaptive Forecasting of Heterogeneous Trajectories

WebLINX: Real-World Website Navigation with Multi-Turn Dialogue

Nash Learning from Human Feedback

Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications

QBMK: Quantum-based Matching Kernels for Un-attributed Graphs

Scalable High-Resolution Pixel-Space Image Synthesis with Hourglass Diffusion Transformers

SIN: Selective and Interpretable Normalization for Long-Term Time Series Forecasting

Evaluating Model Bias Requires Characterizing its Mistakes

Variational Learning is Effective for Large Deep Networks

Learning to Continually Learn with the Bayesian Principle

GliDe with a CaPE: A Low-Hassle Method to Accelerate Speculative Decoding

Conditional Normalizing Flows for Active Learning of Coarse-Grained Molecular Representations

Contrasting Multiple Representations with the Multi-Marginal Matching Gap

Learning Adaptive and View-Invariant Vision Transformer for Real-Time UAV Tracking

Neural Collapse meets Differential Privacy: Curious behaviors of NoisyGD with Near-Perfect Representation Learning

Time Series Diffusion in the Frequency Domain

Interacting Diffusion Processes for Event Sequence Forecasting

BRAIn: Bayesian Reward-conditioned Amortized Inference for natural language generation from feedback

Explorations of Self-Repair in Language Models

Code as Reward: Empowering Reinforcement Learning with VLMs

Learning with 3D rotations, a hitchhiker's guide to SO(3)

On Discrete Prompt Optimization for Diffusion Models

ConvNet vs Transformer, Supervised vs CLIP: Beyond ImageNet Accuracy

Improved Communication-Privacy Trade-offs in $L_2$ Mean Estimation under Streaming Differential Privacy

DoRA: Weight-Decomposed Low-Rank Adaptation

Dynamic Survival Analysis with Controlled Latent States

Pricing with Contextual Elasticity and Heteroscedastic Valuation

CaPS: Collaborative and Private Synthetic Data Generation from Distributed Sources

Asymptotics of Learning with Deep Structured (Random) Features

SaVeR: Optimal Data Collection Strategy for Safe Policy Evaluation in Tabular MDP

Online Adaptive Anomaly Thresholding with Confidence Sequences

Minimum Norm Interpolation Meets The Local Theory of Banach Spaces

Particle Denoising Diffusion Sampler

Diffusion Rejection Sampling

Distributed Bilevel Optimization with Communication Compression

Faster Maximum Inner Product Search in High Dimensions

Learning from Streaming Data when Users Choose

On the Consistency of Kernel Methods with Dependent Observations

Position: Will we run out of data? Limits of LLM scaling based on human-generated data

Careful with that Scalpel: Improving Gradient Surgery with an EMA

Towards Compositionality in Concept Learning

CRoFT: Robust Fine-Tuning with Concurrent Optimization for OOD Generalization and Open-Set OOD Detection

Temporal Logic Specification-Conditioned Decision Transformer for Offline Safe Reinforcement Learning

Model Tailor: Mitigating Catastrophic Forgetting in Multi-modal Large Language Models

By Tying Embeddings You Are Assuming the Distributional Hypothesis

A Diffusion Model Framework for Unsupervised Neural Combinatorial Optimization

OSSCAR: One-Shot Structured Pruning in Vision and Language Models with Combinatorial Optimization

Bridging Model Heterogeneity in Federated Learning via Uncertainty-based Asymmetrical Reciprocity Learning

Model-Free Robust $\phi$-Divergence Reinforcement Learning Using Both Offline and Online Data

How Deep Networks Learn Sparse and Hierarchical Data: the Sparse Random Hierarchy Model

Promptbreeder: Self-Referential Self-Improvement via Prompt Evolution

Provable Privacy with Non-Private Pre-Processing

Scaling Laws for Fine-Grained Mixture of Experts

Improving Generalization in Offline Reinforcement Learning via Adversarial Data Splitting

Various Lengths, Constant Speed: Efficient Language Modeling with Lightning Attention

Conformal prediction for multi-dimensional time series by ellipsoidal sets

Offline Training of Language Model Agents with Functions as Learnable Weights

Controlling Behavioral Diversity in Multi-Agent Reinforcement Learning

Test-Time Regret Minimization in Meta Reinforcement Learning

Leveraging Self-Consistency for Data-Efficient Amortized Bayesian Inference

Asymmetry in Low-Rank Adapters of Foundation Models

Discovering Mixtures of Structural Causal Models from Time Series Data

Theoretical Guarantees for Variational Inference with Fixed-Variance Mixture of Gaussians

Activation-Descent Regularization for Input Optimization of ReLU Networks

Bootstrap AutoEncoders With Contrastive Paradigm for Self-supervised Gaze Estimation

ILILT: Implicit Learning of Inverse Lithography Technologies

Position: Exploring the Robustness of Pipeline-Parallelism-Based Decentralized Training

On a Combinatorial Problem Arising in Machine Teaching

RL-VLM-F: Reinforcement Learning from Vision Language Foundation Model Feedback

Position: The Causal Revolution Needs Scientific Pragmatism

TroVE: Inducing Verifiable and Efficient Toolboxes for Solving Programmatic Tasks

Unsupervised Concept Discovery Mitigates Spurious Correlations

Auctionformer: A Unified Deep Learning Algorithm for Solving Equilibrium Strategies in Auction Games

A Geometric Explanation of the Likelihood OOD Detection Paradox

A Language Model’s Guide Through Latent Space

Identifiability Matters: Revealing the Hidden Recoverable Condition in Unbiased Learning to Rank

The Computational Complexity of Finding Second-Order Stationary Points

Smoothness Adaptive Hypothesis Transfer Learning

FiT: Flexible Vision Transformer for Diffusion Model

Switching the Loss Reduces the Cost in Batch Reinforcement Learning

Image Restoration Through Generalized Ornstein-Uhlenbeck Bridge

Contextualized Policy Recovery: Modeling and Interpreting Medical Decisions with Adaptive Imitation Learning

Enabling Uncertainty Estimation in Iterative Neural Networks

Should we be going MAD? A Look at Multi-Agent Debate Strategies for LLMs

Instruction Tuning for Secure Code Generation

Position: $C^*$-Algebraic Machine Learning $-$ Moving in a New Direction

Rethinking Specificity in SBDD: Leveraging Delta Score and Energy-Guided Diffusion

Swallowing the Bitter Pill: Simplified Scalable Conformer Generation

Quasi-Monte Carlo Features for Kernel Approximation

Provably Better Explanations with Optimized Aggregation of Feature Attributions

Towards Certified Unlearning for Deep Neural Networks

Learning to Model the World With Language

Subgoal-based Demonstration Learning for Formal Theorem Proving

Learning Graph Representation via Graph Entropy Maximization

3D Geometric Shape Assembly via Efficient Point Cloud Matching

An Effective Dynamic Gradient Calibration Method for Continual Learning

MLLM-as-a-Judge: Assessing Multimodal LLM-as-a-Judge with Vision-Language Benchmark

Random features models: a way to study the success of naive imputation

Proteus: Exploring Protein Structure Generation for Enhanced Designability and Efficiency

Practical Hamiltonian Monte Carlo on Riemannian Manifolds via Relativity Theory

Out-of-Domain Generalization in Dynamical Systems Reconstruction

Discounted Adaptive Online Learning: Towards Better Regularization

Absolute Policy Optimization: Enhancing Lower Probability Bound of Performance with High Confidence

Long Range Propagation on Continuous-Time Dynamic Graphs

Debiased Offline Representation Learning for Fast Online Adaptation in Non-stationary Dynamics

Relaxed Quantile Regression: Prediction Intervals for Asymmetric Noise

Unveiling Privacy, Memorization, and Input Curvature Links

Learning to Stabilize Online Reinforcement Learning in Unbounded State Spaces

Extreme Compression of Large Language Models via Additive Quantization

Multiply Robust Estimation for Local Distribution Shifts with Multiple Domains

CompeteAI: Understanding the Competition Dynamics of Large Language Model-based Agents

Et Tu Certifications: Robustness Certificates Yield Better Adversarial Examples

REMEDI: Corrective Transformations for Improved Neural Entropy Estimation

Achieving Margin Maximization Exponentially Fast via Progressive Norm Rescaling

Networked Inequality: Preferential Attachment Bias in Graph Neural Network Link Prediction

All-in-one simulation-based inference

Decomposable Submodular Maximization in Federated Setting

Subsampling is not Magic: Why Large Batch Sizes Work for Differentially Private Stochastic Optimisation

Causal Inference from Competing Treatments

Data-free Neural Representation Compression with Riemannian Neural Dynamics

Restoring balance: principled under/oversampling of data for optimal classification

Dr. Strategy: Model-Based Generalist Agents with Strategic Dreaming

Simple Ingredients for Offline Reinforcement Learning

DNA-SE: Towards Deep Neural-Nets Assisted Semiparametric Estimation

Position: What Can Large Language Models Tell Us about Time Series Analysis

AlphaZero-Like Tree-Search can Guide Large Language Model Decoding and Training

The Stronger the Diffusion Model, the Easier the Backdoor: Data Poisoning to Induce Copyright BreachesWithout Adjusting Finetuning Pipeline

Training Large Language Models for Reasoning through Reverse Curriculum Reinforcement Learning

Improving Open-Ended Text Generation via Adaptive Decoding

DynSyn: Dynamical Synergistic Representation for Efficient Learning and Control in Overactuated Embodied Systems

Training Greedy Policy for Proposal Batch Selection in Expensive Multi-Objective Combinatorial Optimization

Mixtures of Experts Unlock Parameter Scaling for Deep RL

Error Feedback Can Accurately Compress Preconditioners

Position: A Roadmap to Pluralistic Alignment

Superposition Prompting: Improving and Accelerating Retrieval-Augmented Generation

Implicit Regularization in Feedback Alignment Learning Mechanisms for Neural Networks

Variational Schrödinger Diffusion Models

Learning to Remove Cuts in Integer Linear Programming

Benign Overfitting in Two-Layer ReLU Convolutional Neural Networks for XOR Data

Understanding Server-Assisted Federated Learning in the Presence of Incomplete Client Participation

Active Adaptive Experimental Design for Treatment Effect Estimation with Covariate Choice

LLaGA: Large Language and Graph Assistant

Knowledge-aware Reinforced Language Models for Protein Directed Evolution

CogDPM: Diffusion Probabilistic Models via Cognitive Predictive Coding

tinyBenchmarks: evaluating LLMs with fewer examples

Predicting and Interpreting Energy Barriers of Metallic Glasses with Graph Neural Networks

Disentangled Continual Graph Neural Architecture Search with Invariant Modular Supernet

A Statistical Framework for Data-dependent Retrieval-Augmented Models

Do Large Language Models Perform the Way People Expect? Measuring the Human Generalization Function

Neural Networks Learn Statistics of Increasing Complexity

GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection

video-SALMONN: Speech-Enhanced Audio-Visual Large Language Models

FRAG: Frequency Adapting Group for Diffusion Video Editing

Online Algorithms with Uncertainty-Quantified Predictions

On Which Nodes Does GCN Fail? Enhancing GCN From the Node Perspective

On the Error-Propagation of Inexact Hotelling's Deflation for Principal Component Analysis

Learning to Predict Mutational Effects of Protein-Protein Interactions by Microenvironment-aware Hierarchical Prompt Learning

Data Engineering for Scaling Language Models to 128K Context

Conformal Validity Guarantees Exist for Any Data Distribution (and How to Find Them)

FedREDefense: Defending against Model Poisoning Attacks for Federated Learning using Model Update Reconstruction Error

Bounding the Excess Risk for Linear Models Trained on Marginal-Preserving, Differentially-Private, Synthetic Data

Weisfeiler-Leman at the margin: When more expressivity matters

Generalized Neural Collapse for a Large Number of Classes

Initial Guessing Bias: How Untrained Networks Favor Some Classes

On The Statistical Complexity of Offline Decision-Making

DiffAug: Enhance Unsupervised Contrastive Learning with Domain-Knowledge-Free Diffusion-based Data Augmentation

Helpful or Harmful Data? Fine-tuning-free Shapley Attribution for Explaining Language Model Predictions

On the Sample Complexity and Metastability of Heavy-tailed Policy Search in Continuous Control

Achieving Lossless Gradient Sparsification via Mapping to Alternative Space in Federated Learning

Unsupervised Domain Adaptation for Anatomical Structure Detection in Ultrasound Images

Can Implicit Bias Imply Adversarial Robustness?

Entropy-Reinforced Planning with Large Language Models for Drug Discovery

EfficientZero V2: Mastering Discrete and Continuous Control with Limited Data

Removing Spurious Concepts from Neural Network Representations via Joint Subspace Estimation

A Touch, Vision, and Language Dataset for Multimodal Alignment

Approximate Nearest Neighbor Search with Window Filters

Learning from Integral Losses in Physics Informed Neural Networks

How Interpretable Are Interpretable Graph Neural Networks?

GPTSwarm: Language Agents as Optimizable Graphs

OpenMoE: An Early Effort on Open Mixture-of-Experts Language Models

Learning Mixtures of Gaussian Processes through Random Projection

Private and Federated Stochastic Convex Optimization: Efficient Strategies for Centralized Systems

MolCRAFT: Structure-Based Drug Design in Continuous Parameter Space

Foundation Policies with Hilbert Representations

On Interpolating Experts and Multi-Armed Bandits

Position: Optimization in SciML Should Employ the Function Space Geometry

Language Models Represent Beliefs of Self and Others

Learning Useful Representations of Recurrent Neural Network Weight Matrices

Smooth Min-Max Monotonic Networks

Efficient PAC Learnability of Dynamical Systems Over Multilayer Networks

Consistent Diffusion Meets Tweedie: Training Exact Ambient Diffusion Models with Noisy Data

Use Your INSTINCT: INSTruction optimization for LLMs usIng Neural bandits Coupled with Transformers

Averaging $n$-step Returns Reduces Variance in Reinforcement Learning

Graph Neural Networks with a Distribution of Parametrized Graphs

Position: Graph Foundation Models Are Already Here

Seesaw: Compensating for Nonlinear Reduction with Linear Computations for Private Inference

Efficient Stochastic Approximation of Minimax Excess Risk Optimization

Adaptively Perturbed Mirror Descent for Learning in Games

Accurate LoRA-Finetuning Quantization of LLMs via Information Retention

Risk Estimation in a Markov Cost Process: Lower and Upper Bounds

A Resilient and Accessible Distribution-Preserving Watermark for Large Language Models

CW Complex Hypothesis for Image Data

Fast Text-to-3D-Aware Face Generation and Manipulation via Direct Cross-modal Mapping and Geometric Regularization

Stability Evaluation through Distributional Perturbation Analysis

Adapting Static Fairness to Sequential Decision-Making: Bias Mitigation Strategies towards Equal Long-term Benefit Rate

Can We Remove the Square-Root in Adaptive Gradient Methods? A Second-Order Perspective

RNAFlow: RNA Structure & Sequence Design via Inverse Folding-Based Flow Matching

RODEO: Robust Outlier Detection via Exposing Adaptive Out-of-Distribution Samples

Estimating the Permanent by Nesting Importance Sampling

LoRA Training in the NTK Regime has No Spurious Local Minima

NeuralIndicator: Implicit Surface Reconstruction from Neural Indicator Priors

Bridging Mini-Batch and Asymptotic Analysis in Contrastive Learning: From InfoNCE to Kernel-Based Losses

Boundary Exploration for Bayesian Optimization With Unknown Physical Constraints

A Unified Framework for Learning with Nonlinear Model Classes from Arbitrary Linear Samples

Privacy Backdoors: Stealing Data with Corrupted Pretrained Models

A Tensor Decomposition Perspective on Second-order RNNs

Inherent Trade-Offs between Diversity and Stability in Multi-Task Benchmarks

UP2ME: Univariate Pre-training to Multivariate Fine-tuning as a General-purpose Framework for Multivariate Time Series Analysis

Applying language models to algebraic topology: generating simplicial cycles using multi-labeling in Wu's formula

Spike Distance Function as a Learning Objective for Spike Prediction

Unsupervised Representation Learning of Brain Activity via Bridging Voxel Activity and Functional Connectivity

Total Variation Distance Meets Probabilistic Inference

On the Maximal Local Disparity of Fairness-Aware Classifiers

Diffusive Gibbs Sampling

Policy Evaluation for Variance in Average Reward Reinforcement Learning

T-Cal: An Optimal Test for the Calibration of Predictive Models

Towards Interpretable Deep Local Learning with Successive Gradient Reconciliation

Hard Tasks First: Multi-Task Reinforcement Learning Through Task Scheduling

Executable Code Actions Elicit Better LLM Agents

Regression with Multi-Expert Deferral

Multi-layer Rehearsal Feature Augmentation for Class-Incremental Learning

(ends 6:00 AM)

6 a.m.

Invited Talk:

Lucilla Sioli

(ends 7:00 AM)

7 a.m.

Break:

Coffee Break

(ends 7:30 AM)

7:30 a.m.

Oral 6x Experimental Design and Simulation [7:30-8:30]

Orals 7:30-8:30

[7:30] Active Adaptive Experimental Design for Treatment Effect Estimation with Covariate Choice

[7:45] All-in-one simulation-based inference

[8:00] Privacy Preserving Adaptive Experiment Design

[8:15] Environment Design for Inverse Reinforcement Learning

(ends 8:30 AM)

Oral 6x Low Rank Learning [7:30-8:30]

Orals 7:30-8:30

[7:30] Accurate LoRA-Finetuning Quantization of LLMs via Information Retention

[7:45] DoRA: Weight-Decomposed Low-Rank Adaptation

[8:00] GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection

[8:15] LoRA Training in the NTK Regime has No Spurious Local Minima

(ends 8:30 AM)

Oral 6x Multimodal Learning [7:30-8:30]

Orals 7:30-8:30

[7:30] NExT-GPT: Any-to-Any Multimodal LLM

[7:45] MLLM-as-a-Judge: Assessing Multimodal LLM-as-a-Judge with Vision-Language Benchmark

[8:00] FedMBridge: Bridgeable Multimodal Federated Learning

[8:15] A Touch, Vision, and Language Dataset for Multimodal Alignment

(ends 8:30 AM)

Oral 6x Representation Learning 2 [7:30-8:30]

Orals 7:30-8:30

[7:30] Learning Useful Representations of Recurrent Neural Network Weight Matrices

[7:45] Data-free Neural Representation Compression with Riemannian Neural Dynamics

[8:00] Neural Collapse meets Differential Privacy: Curious behaviors of NoisyGD with Near-Perfect Representation Learning

[8:15] Contrasting Multiple Representations with the Multi-Marginal Matching Gap

(ends 8:30 AM)

Oral 6x Agents and World Modeling [7:30-8:30]

Orals 7:30-8:30

[7:30] Position: Open-Endedness is Essential for Artificial Superhuman Intelligence

[7:45] Learning to Model the World With Language

[8:00] CompeteAI: Understanding the Competition Dynamics of Large Language Model-based Agents

[8:15] GPTSwarm: Language Agents as Optimizable Graphs

(ends 8:30 AM)

Oral 6x Robustness and Safety [7:30-8:30]

Orals 7:30-8:30

[7:30] The Stronger the Diffusion Model, the Easier the Backdoor: Data Poisoning to Induce Copyright BreachesWithout Adjusting Finetuning Pipeline

[7:45] Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models

[8:00] Towards Optimal Adversarial Robust Q-learning with Bellman Infinity-error

[8:15] Scalable AI Safety via Doubly-Efficient Debate

(ends 8:30 AM)

11 p.m.

Registration

(ends 7:00 AM)

11:30 p.m.

Break:

Coffee Break

(ends 12:00 AM)

FRI 26 JUL

midnight

Workshop:

Models of Human Feedback for AI Alignment

(ends 8:00 AM)

Workshop:

Next Generation of AI Safety

(ends 8:00 AM)

Workshop:

Structured Probabilistic Inference and Generative Modeling

(ends 8:00 AM)

Workshop:

Machine Learning for Earth System Modeling: Accelerating Pathways to Impact

(ends 8:00 AM)

Workshop:

AI for Math Workshop

(ends 8:00 AM)

Workshop:

Differentiable Almost Everything: Differentiable Relaxations, Algorithms, Operators, and Simulators

(ends 8:00 AM)

Workshop:

ICML 2024 Workshop on Foundation Models in the Wild

(ends 8:00 AM)

Workshop:

ML for Life and Material Science: From Theory to Industry Applications

(ends 8:00 AM)

Workshop:

Multi-modal Foundation Model meets Embodied AI (MFM-EAI)

(ends 8:00 AM)

Workshop:

Next Generation of Sequence Modeling Architectures

(ends 8:00 AM)

Workshop:

Aligning Reinforcement Learning Experimentalists and Theorists

(ends 8:00 AM)

Workshop:

ES-FoMo II: 2nd Workshop on Efficient Systems for Foundation Models

(ends 8:00 AM)

Workshop:

Long-Context Foundation Models

(ends 8:00 AM)

Workshop:

AI for Science: Scaling in AI for Scientific Discovery

(ends 8:00 AM)

Workshop:

High-dimensional Learning Dynamics Workshop: The Emergence of Structure and Reasoning

(ends 8:00 AM)

3:30 a.m.

Break:

Hosted Lunch

(ends 5:00 AM)

6:30 a.m.

Break:

Coffee Break

(ends 7:00 AM)

11 p.m.

Registration

(ends 2:00 AM)

11:30 p.m.

Break:

Coffee Break

(ends 12:00 AM)

SAT 27 JUL

midnight

Workshop:

Foundations of Reinforcement Learning and Control: Connections and Perspectives

(ends 8:00 AM)

Workshop:

Trustworthy Multi-modal Foundation Models and AI Agents (TiFA)

(ends 8:00 AM)

Workshop:

Workshop on Mechanistic Interpretability

(ends 8:00 AM)

Workshop:

Workshop on Theoretical Foundations of Foundation Models (TF2M)

(ends 8:00 AM)

Workshop:

2nd Workshop on Generative AI and Law (GenLaw ’24)

(ends 8:00 AM)

Workshop:

Automated Reinforcement Learning: Exploring Meta-Learning, AutoML, and LLMs

(ends 8:00 AM)

Workshop:

Data-centric Machine Learning Research (DMLR): Datasets for Foundation Models

(ends 8:00 AM)

Workshop:

ICML Workshop on Large Language Models and Cognition

(ends 8:00 AM)

Workshop:

1st ICML Workshop on In-Context Learning (ICL @ ICML 2024)

(ends 8:00 AM)

Workshop:

Agentic Markets Workshop

(ends 8:00 AM)

Workshop:

Text, camera, action! Frontiers in controllable video generation

(ends 8:00 AM)

Workshop:

Accessible and Efficient Foundation Models for Biological Discovery

(ends 8:00 AM)

Workshop:

Humans, Algorithmic Decision-Making and Society: Modeling Interactions and Impact

(ends 8:00 AM)

Workshop:

2nd Workshop on Advancing Neural Network Training : Computational Efficiency, Scalability, and Resource Optimization (WANT@ICML 2024)

(ends 8:00 AM)

Workshop:

Geometry-grounded Representation Learning and Generative Modeling

(ends 8:00 AM)

3:30 a.m.

Break:

Hosted Lunch

(ends 5:00 AM)

6:30 a.m.

Break:

Coffee Break

(ends 7:00 AM)