| Show Detail |
Timezone: Asia/Seoul
|
Filter Rooms:
SUN 5 JUL
2 p.m.
(ends 7:30 PM)
MON 6 JUL
7 a.m.
(ends 6:00 PM)
8 a.m.
Expo Talk Panel:
(ends 9:00 AM)
8:30 a.m.
9 a.m.
11:30 a.m.
Expo Talk Panel:
(ends 12:30 PM)
Expo Talk Panel:
(ends 12:30 PM)
Expo Talk Panel:
(ends 12:30 PM)
Expo Talk Panel:
(ends 12:30 PM)
noon
12:30 p.m.
Expo Demonstration:
(ends 2:30 PM)
Expo Demonstration:
(ends 2:30 PM)
Expo Demonstration:
(ends 2:30 PM)
Expo Demonstration:
(ends 2:30 PM)
Expo Demonstration:
(ends 2:30 PM)
1:30 p.m.
Tutorial:
(ends 4:00 PM)
Tutorial:
(ends 4:00 PM)
3:30 p.m.
4 p.m.
Expo Workshop:
(ends 7:00 PM)
Expo Workshop:
(ends 7:00 PM)
Expo Workshop:
(ends 7:00 PM)
Expo Workshop:
(ends 7:00 PM)
TUE 7 JUL
7:30 a.m.
(ends 6:00 PM)
8:30 a.m.
9:30 a.m.
10 a.m.
Orals 10:00-11:00
[10:00]
Do We Need Adam? Surprisingly Strong and Sparse Reinforcement Learning with SGD in LLMs
[10:15]
Learning Unmasking Policies for Diffusion Language Models
[10:30]
Less is Enough: Synthesizing Diverse Data in Feature Space of LLMs
[10:45]
OPUS: Towards Efficient and Principled Data Selection in Large Language Model Pre-training in Every Iteration
(ends 11:00 AM)
Orals 10:00-11:00
[10:00]
Benchmarking at the Edge of Comprehension
[10:15]
daVinci-Dev: Agent-native Mid-training for Software Engineering
[10:30]
Strategic Navigation or Stochastic Search? How Agents and Humans Reason Over Document Collections
[10:45]
VenusBench-Mobile: A Challenging and User-Centric Benchmark for Mobile GUI Agents with Capability Diagnostics
(ends 11:00 AM)
Orals 10:00-11:00
[10:00]
dnaHNet: A Scalable and Hierarchical Foundation Model for Genomic Sequence Learning
[10:15]
FLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications
[10:30]
Protein Autoregressive Modeling via Multiscale Structure Generation
[10:45]
Protein Fold Classification at Scale: Benchmarking and Pretraining
(ends 11:00 AM)
Orals 10:00-11:00
[10:00]
DiScoFormer: Plug-In Density and Score Estimation with Transformers
[10:15]
LASER: Learning Active Sensing for Continuum Field Reconstruction
[10:30]
Multimodal Nested Learning for Decoupled and Coordinated Optimization
[10:45]
Riemannian Metric Matching for Scalable Geometric Modeling of Distributions
(ends 11:00 AM)
Orals 10:00-11:00
[10:00]
Position: Don't Just "Fix it in Post'': A Science of AI Must Study Learning Dynamics
[10:15]
A Systematic Study of Behavioral Cloning for Scientific Data Annotation
[10:30]
AI Engram: In Search of Memory Traces in Artificial Intelligence
[10:45]
Guaranteed Optimal Compositional Explanations for Neurons
(ends 11:00 AM)
Orals 10:00-11:00
[10:00]
Are VLMs Seeing or Just Saying? Uncovering the Illusion of Visual Re-examination
[10:15]
CLEAR: Context-Aware Learning with End-to-End Mask-Free Inference for Adaptive Subtitle Removal
[10:30]
Motion Attribution for Video Generation
[10:45]
PhotoAgent: Exploratory Visual Aesthetic Planning with Large Vision Models
(ends 11:00 AM)
Orals 10:00-11:00
[10:00]
Asymmetric Perturbation in Solving Bilinear Saddle-Point Optimization
[10:15]
Mixtures Closest To A Given Measure: A Semidefinite Programming Approach
[10:30]
On the Convergence Rate of LoRA Gradient Descent
[10:45]
Revenue Efficiency of Correlated Equilibria in First Price Auctions
(ends 11:00 AM)
10:30 a.m.
Posters 10:30-12:15
Cross-Chirality Generalization by Axial Vectors for Hetero-Chiral Protein-Peptide Interaction Design
Kuramoto Oscillatory Phase Encoding: Neuro-inspired Synchronization for Improved Learning Efficiency
UrbanFusion: Stochastic Multimodal Fusion for Contrastive Learning of Robust Spatial Representations
Row-stochastic matrices can provably outperform doubly stochastic matrices in decentralized learning
(ends 12:15 PM)
noon
1:30 p.m.
Orals 1:30-2:30
[1:30]
Controlled LLM Training on Spectral Sphere
[1:45]
Detecting the Semantic Fixed Point: A Geometric Framework for Efficient Inference
[2:00]
ECHO: Elastic Speculative Decoding with Sparse Gating for High-Concurrency Scenarios
[2:15]
MuonSSM: Orthogonalizing State Space Models for Sequence Modeling
(ends 2:30 PM)
Orals 1:30-2:30
[1:30]
Don't Force the Fit: Bounded Log-Likelihood Loss for Enhanced Reasoning in Large Language Models
[1:45]
Evaluating Robustness of Reasoning Models on Parameterized Logical Problems
[2:00]
TG-RAG: A Retrieval-Augmented Framework for Reasoning Guidance in Specialized Domains
[2:15]
Understanding Reasoning Collapse in LLM Agent Reinforcement Learning
(ends 2:30 PM)
Orals 1:30-2:30
[1:30]
Position: Anthropomorphic Misalignment Research Needs Stronger Evidence
[1:45]
Monitoring Monitorability
[2:00]
The Obfuscation Atlas: Mapping Where Honesty Emerges in RLVR with Deception Probes
[2:15]
VALUEFLOW: Toward Pluralistic and Steerable Value-based Alignment in Large Language Models
(ends 2:30 PM)
Orals 1:30-2:30
[1:30]
From Feasible to Practical: Pareto-Optimal Synthesis Planning
[1:45]
ReViT: Rotational-equivariant Vision Transformers for Neural PDE Solvers
[2:00]
Rex: A Family of Reversible Exponential (Stochastic) Runge-Kutta Solvers
[2:15]
Towards Sub-second Biological Foundation Model Infrastructure: A Quantized Consistency Diffusion Framework for Molecular Docking
(ends 2:30 PM)
Orals 1:30-2:30
[1:30]
Chebyshev Policies and the Mountain Car Problem: Reinforcement Learning for Low-dimensional Control Tasks
[1:45]
Maximum Likelihood Reinforcement Learning
[2:00]
Minimax Optimal Strategy for Delayed Observations in Online Reinforcement Learning
[2:15]
Optimal Decision-Making Based on Prediction Sets
(ends 2:30 PM)
Orals 1:30-2:30
[1:30]
Learning Human-Robot Collaboration via Heterogeneous-Agent Lyapunov Policy Optimization
[1:45]
Optimal and Scalable MAPF via Multi-Marginal Optimal Transport and Schrödinger Bridges
[2:00]
RoboMME: Benchmarking and Understanding Memory for Robotic Generalist Policies
[2:15]
Unsupervised Partner Design Enables Robust Ad-hoc Teamwork
(ends 2:30 PM)
Orals 1:30-2:30
[1:30]
Diffract: Spectral View of LLM Domain Adaptation
[1:45]
Foundations of Equivariant Deep Learning: Unifying Graph and Sheaf Neural Networks
[2:00]
On Minimum Depth and Width of Floating-Point Neural Networks for Representing Floating-Point Functions
[2:15]
The Expressivity Limits of Transformers
(ends 2:30 PM)
2 p.m.
Posters 2:00-3:45
Can Recommender Systems Teach Themselves? A Recursive Self-Improving Framework with Fidelity Control
Large-Scale Molecular Dynamics Simulations: Direct Interatomic Modeling with Dilated Message Passing
StarEmbed: Benchmarking Time Series Foundation Models on Astronomical Observations of Variable Stars
Learning the Interaction Prior for Protein-Protein Interaction Prediction: A Model-Agnostic Approach
MICE-Bench: A Challenging and Comprehensive Benchmark for Multi-Reference Image Creation and Editing
ParEVO: Synthesizing Code for Irregular Data: High-Performance Parallelism through Agentic Evolution
Selective Deferred Routing: Enabling Cost-Efficient Collaboration between Local SLMs and Remote LLMs
Towards Fine-grained Robustness: Attention-guided Test-time Prompt Tuning for Vision-Language Models
MiniAppBench: Evaluating the Shift from Text to Interactive HTML Responses in LLM-Powered Assistants
Contrastive Symbolic Regression: Aligned Representations, Adaptive Prediction, and Diverse Ensembles
Revisiting Distribution Correction Estimation for Offline Imitation Learning with Suboptimal Dataset
Position: Express Your Doubts — Probabilistic World Modeling Should not be Based on Token *logprobs*
Hallucination is a Consequence of Space-Optimality: A Rate-Distortion Theorem for Membership Testing
(ends 3:45 PM)
3 p.m.
4 p.m.
5 p.m.
5:45 p.m.
WED 8 JUL
7:30 a.m.
(ends 6:00 PM)
8:30 a.m.
Invited Talk:
Sham Kakade
(ends 9:30 AM)
9:30 a.m.
10 a.m.
Orals 10:00-11:00
[10:00]
Any-Order GPT as Masked Diffusion Model: Decoupling Formulation and Architecture
[10:15]
Error Propagation Mechanisms and Compensation Strategies for Quantized Diffusion Models
[10:30]
High-accuracy and dimension-free sampling with diffusions
[10:45]
The Flexibility Trap: Rethinking the Value of Arbitrary Order in Diffusion Language Models
(ends 11:00 AM)
Orals 10:00-11:00
[10:00]
Mitigating Reward Hacking in RLHF via Bayesian Non-negative Reward Modeling
[10:15]
Reinforcement Learning with Evolving Rubrics for Deep Research
[10:30]
Simultaneous Speech-to-Speech Translation Without Aligned Data
[10:45]
Video-Based Optimal Transport for Feedback-Efficient Offline Preference-Based Reinforcement Learning
(ends 11:00 AM)
Orals 10:00-11:00
[10:00]
Position: AI Should Facilitate Democratic Deliberation at Scale
[10:15]
Activation Oracles: Training and Evaluating LLMs as General-Purpose Activation Explainers
[10:30]
Large Language Models Develop Novel Social Biases Through Adaptive Exploration
[10:45]
Mechanistic Data Attribution: Tracing the Training Origins of Interpretable LLM Units
(ends 11:00 AM)
Orals 10:00-11:00
[10:00]
Bad Seeing or Bad Thinking? Rewarding Perception for Multimodal Reasoning
[10:15]
DroneDINO: Towards Heterogeneous Routed Mixture of Experts for Drone-based Unified Object Detection
[10:30]
Lottery Prior: Randomized Neural Compression for Zero-Shot Inverse Problems
[10:45]
Scalable Event Cloud Network for Event-based Classification
(ends 11:00 AM)
Orals 10:00-11:00
[10:00]
Position: Stop Automating Peer Review Without Rigorous Evaluation
[10:15]
Position: The AI Imperative: Scaling High-Quality Peer Review in Machine Learning
[10:30]
Incentivizing Truthfulness and Collaborative Fairness in Bayesian Learning
[10:45]
Is Your LLM Overcharging You? Tokenization, Transparency, and Incentives
(ends 11:00 AM)
Orals 10:00-11:00
[10:00]
Jailbreak Foundry: From Papers to Runnable Attacks for Reproducible Benchmarking
[10:15]
Quantifying Frontier LLM Capabilities for Container Sandbox Escape
[10:30]
Robust Harmful Features Under Jailbreak Attacks: Mechanistic Evidence from Attention Head Specialization in Large Language Models
[10:45]
When the Prompt Becomes Visual: Vision-Centric Jailbreak Attacks for Large Image Editing Models
(ends 11:00 AM)
Orals 10:00-11:00
[10:00]
Exact Functional ANOVA Decomposition for Categorical Inputs
[10:15]
Joint Learning in the Gaussian Single Index Model
[10:30]
SVRG and Beyond via Posterior Correction
[10:45]
Towards Fair Sequential Decision-Making: A Causal Decomposition Approach
(ends 11:00 AM)
10:30 a.m.
Posters 10:30-12:15
EqGINO: Equivariant Geometry-Informed Fourier Neural Operators for 3D Partial Differential Equations
BESPOKE: Benchmark for Search-Augmented Large Language Model Personalization via Diagnostic Feedback
From Per-Image Low-Rank to Encoding Mismatch: Rethinking Feature Distillation in Vision Transformers
Unsat Core Prediction through Polarity-Aware Representation Learning over Clause-Literal Hypergraphs
Towards Complete Multi-Agent Coordination Policy Learning via Denoising Maximum Entropy Optimization
(ends 12:15 PM)
noon
1:30 p.m.
2:30 p.m.
Posters 2:30-4:15
CauseCollab: Causal Unified and Modality-Agnostic Network for Heterogeneous Collaborative Perception
Semi-LAR: Semi-supervised Contrastive Learning with Linear Attention for Removal of Nighttime Flares
Fixed Budget is No Harder Than Fixed Confidence in Best-Arm Identification up to Logarithmic Factors
Learning Interpretable Options by Identifying Reward Diffusion Bottlenecks in Reinforcement Learning
Compositional Transduction with Latent Analogies for Offline Goal-Conditioned Reinforcement Learning
Video-Based Optimal Transport for Feedback-Efficient Offline Preference-Based Reinforcement Learning
(ends 4:15 PM)
3 p.m.
4 p.m.
Orals 4:00-5:00
[4:00]
CAT-Q: Cost-efficient and Accurate Ternary Quantization for LLMs
[4:15]
POET-X: Memory-efficient LLM Training by Scaling Orthogonal Transformation
[4:30]
ReQAT: Achieving Full-Precision Reasoning Accuracy with 4-bit Floating-Point Quantization-Aware Training
[4:45]
Skip a Layer or Loop It? Learning Program-of-Layers in LLMs
(ends 5:00 PM)
Orals 4:00-5:00
[4:00]
From Abstraction to Instantiation: Learning Behavioral Representation for Vision-Language-Action Model
[4:15]
From Pixels to Tokens: A Systematic Study of Latent Action Supervision for Vision-Language-Action Models
[4:30]
Pretrained Vision-Language-Action Models are Surprisingly Resistant to Forgetting in Continual Learning
[4:45]
XR-1: Towards Versatile Vision-Language-Action Models via Learning Unified Vision-Motion Representations
(ends 5:00 PM)
Orals 4:00-5:00
[4:00]
Position: The Alignment Community is Unintentionally Building a Censor’s Toolkit
[4:15]
Information Flow Reveals When to Trust Language Models
[4:30]
Modeling Hierarchical Thinking in Large Reasoning Models
[4:45]
Reward-free Alignment for Conflicting Objectives
(ends 5:00 PM)
Orals 4:00-5:00
[4:00]
A Recursive Decomposition Framework for Causal Structure Learning in the Presence of Latent Variables
[4:15]
DISCO: Mitigating Bias in Deep Learning with Conditional Distance Correlation
[4:30]
Disentangling Latent Risk Pathways via Bayesian Hypergraph Inference
[4:45]
On the Identifiability of Poisson Branching Structural Causal Model Under Latent Confounding
(ends 5:00 PM)
Orals 4:00-5:00
[4:00]
CoEvol-NO: State and Coordinate Co-Evolution with an Error-Driven Predictor-Corrector Paradigm for Neural Operator Transformer
[4:15]
Geometric Flow Grounding: A Unified Manifold Decoupling Framework for Dynamics Discovery and Verification
[4:30]
Solving Time-Dependent Differential Equations with Physical Dynamical Systems
[4:45]
Training-Free Bayesian Filtering with Generative Emulators
(ends 5:00 PM)
Orals 4:00-5:00
[4:00]
DPO Unchained: Your Training Algorithm is Secretly Disentangled in Human Choice Theory (and Its Loss' Convexity is Dispensable)
[4:15]
High-accuracy sampling for diffusion models and log-concave distributions
[4:30]
Rational Transductors
[4:45]
To Grok Grokking: Provable Grokking in Ridge Regression
(ends 5:00 PM)
Orals 4:00-5:00
[4:00]
ConFlux: Multivariate Time Series in Flux, One Unified Forecast in Confluence
[4:15]
From Text to Forecasts: Bridging Modality Gap with Temporal Evolution Semantic Space
[4:30]
Markov Chain Monte Carlo without Evaluating the Target: an Auxiliary Variable Approach
[4:45]
Path-dependent Discrete Amortized Inference
(ends 5:00 PM)
5 p.m.
Posters 5:00-6:45
SCALE: Self-uncertainty Conditioned Adaptive Looking and Execution for Vision-Language-Action Models
General Covariant Action Modeling: Constructing Generalized Manifolds via Spatio-Temporal Decoupling
LLM-MatLogic: Executable Exchange Contracts for Knowledge-Graph Query Answering with Scoped Negation
Distinguishable Deletion: Unifying Knowledge Erasure and Refusal for Large Language Model Unlearning
Addressing Instrument-Outcome Confounding in Mendelian Randomization through Representation Learning
(ends 6:45 PM)
7 p.m.
THU 9 JUL
7:30 a.m.
(ends 6:00 PM)
8:30 a.m.
Invited Talk:
Verena Rieser
(ends 9:30 AM)
9:30 a.m.
10 a.m.
Orals 10:00-11:00
[10:00]
Midtraining Bridges Pretraining and Posttraining Distributions
[10:15]
ThreadWeaver: Adaptive Threading for Efficient Parallel Reasoning in Language Models
[10:30]
TokSuite: Measuring the Impact of Tokenizer Choice on Language Model Behavior
[10:45]
WeDLM: Reconciling Diffusion Language Models with Standard Causal Attention for Fast Inference
(ends 11:00 AM)
Orals 10:00-11:00
[10:00]
Mind Your Margin and Boundary: Are Your Distilled Datasets Truly Robust?
[10:15]
On the Difficulty of Learning a Meta-network for Training Data Selection
[10:30]
The Signal is in the Steps: Local Scoring for Reasoning Data Selection
[10:45]
Transforming Weather Data from Pixel to Latent Space
(ends 11:00 AM)
Orals 10:00-11:00
[10:00]
Distributional Inverse Reinforcement Learning
[10:15]
On Computation and Reinforcement Learning
[10:30]
Second-Order Smooth Planning with Optimal-Transport Bellman Smoothing
[10:45]
Stabilizing the Q-Gradient Field for Policy Smoothness in Actor-Critic Methods
(ends 11:00 AM)
Orals 10:00-11:00
[10:00]
Position: There are futures that benchmark-driven AI cannot see
[10:15]
CausalGame: Benchmarking Causal Thinking of LLM Agents in Games
[10:30]
Characterizing, Evaluating, and Optimizing Complex Reasoning
[10:45]
Rare Event Analysis of Large Language Models
(ends 11:00 AM)
Orals 10:00-11:00
[10:00]
Necessary Conditions for Compositional Generalization of Embedding Models
[10:15]
Non-Euclidean Gradient Descent Operates at the Edge of Stability
[10:30]
PRISM: Gauge-Invariant Tangent-Space Differentially Private LoRA
[10:45]
Robust Contextual Optimization with Missing Covariates
(ends 11:00 AM)
Orals 10:00-11:00
[10:00]
FlatLand: Personalized Graph Federated Learning via Tailored Lorentz Space
[10:15]
MV-FGAD: Towards Efficient and Effective Federated Graph Anomaly Detection via Multi-view Learning
[10:30]
PhenoBrain: Phenotype-Conditioned Long-Range Communication for Multi-Modal Brain Network Analysis
[10:45]
Towards Hierarchy–Uniformity Equilibrium: Recovering Semantic Depth in Hypergraph Contrastive Learning
(ends 11:00 AM)
Orals 10:00-11:00
[10:00]
3ViewSense: Spatial and Mental Perspective Reasoning from Orthographic Views in Vision-Language Models
[10:15]
Agent0-VL: Exploring Self-Evolving Agent for Tool-Integrated Vision-Language Reasoning
[10:30]
Holi-Spatial: Evolving Video Streams into Holistic 3D Spatial Intelligence
[10:45]
SpatioLM: Towards General Physical Spatial Intelligence in Vision-Language Models
(ends 11:00 AM)
10:30 a.m.
Posters 10:30-12:15
AVGen-Bench: A Task-Driven Benchmark for Multi-Granular Evaluation of Text-to-Audio-Video Generation
Rethinking the Reranker: Boundary-Aware Evidence Selection for Robust Retrieval-Augmented Generation
T$^2$PO: Uncertainty-Guided Exploration Control for Stable Multi-Turn Agentic Reinforcement Learning
(ends 12:15 PM)
noon
1:30 p.m.
2:30 p.m.
Posters 2:30-4:15
Taming I2V models for Image HOI Editing: A Cognitive Benchmark and Agentic Self-Correcting Framework
World-Model Inspired Emotion-aware Token Refinement for Training-Free Multimodal Emotion Recognition
ReVSI: Rebuilding Visual Spatial Intelligence Evaluation for Accurate Assessment of VLM 3D Reasoning
Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoning
Does a Hybrid Space-Aware Randomized Defense Improve Empirical and Certified Adversarial Robustness?
From Interaction Trajectories to Prompt Rules: Credit Assignment for Multi-Agent Prompt Optimization
(ends 4:15 PM)
3 p.m.
4 p.m.
Orals 4:00-5:00
[4:00]
Expressivity-Efficiency Tradeoffs for Hybrid Sequence Models
[4:15]
How much can language models memorize?
[4:30]
Prescriptive Scaling Reveals the Evolution of Language Model Capabilities
[4:45]
Procedural Pretraining: Warming Up Language Models with Abstract Data
(ends 5:00 PM)
Orals 4:00-5:00
[4:00]
$\tau^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment
[4:15]
Characterizing Agents in Production
[4:30]
CVE-Factory: Scaling Expert-Level Agentic Tasks for Code Security Vulnerability
[4:45]
OMAC: A Holistic Optimization Framework for LLM-Based Multi-Agent Collaboration
(ends 5:00 PM)
Orals 4:00-5:00
[4:00]
DOUBT: Decoupled Object-level Understanding and Bridging via vMF-based Trustworthiness for Hallucination Detection in MLLMs
[4:15]
Learning to Theorize the World from Observation
[4:30]
On the Limits of LLM Adaptability: Impact of LLM Pre-Training on Annotation Task Performance
[4:45]
Towards Long-Horizon Interpretability: Efficient and Faithful Multi-Token Attribution for Reasoning LLMs
(ends 5:00 PM)
Orals 4:00-5:00
[4:00]
Faster Activation Functions at the Edge for Post-Training Speedups
[4:15]
FlashSinkhorn: IO-Aware Entropic Optimal Transport on GPU
[4:30]
FlashSketch: Sketch-Kernel Co-Design for Fast Sparse Sketching on GPUs
[4:45]
SoftJAX & SoftTorch: Empowering Automatic Differentiation Libraries with Informative Gradients
(ends 5:00 PM)
Orals 4:00-5:00
[4:00]
Position: Irresponsible AI: big tech’s influence on AI research and associated impacts
[4:15]
Equilibrium Pricing in Oligopolistic Data Markets
[4:30]
Nash Equilibria in Games with Playerwise Concave Coupling Constraints: Existence and Computation
[4:45]
What Preferences Can—and Cannot—Predict in Multi-Agent Online Learning
(ends 5:00 PM)
Orals 4:00-5:00
[4:00]
Position: AI/ML Deepfake Research is Misaligned with AI Generated Non-Consensual Intimate Imagery (AIG-NCII)
[4:15]
GoodDiffusion: Proactive Copyright Protection for Diffusion Generative Models via Learnable Sample-specific Signatures
[4:30]
Orthogonal Concept Erasure for Diffusion Models
[4:45]
Privacy-Aware Video Anomaly Detection: Guided Orthogonal Projection and a Comprehensive Evaluation Framework
(ends 5:00 PM)
Orals 4:00-5:00
[4:00]
A Random Matrix Perspective on the Consistency of Diffusion Models
[4:15]
Equivalence of Context and Parameter Updates in Modern Transformer Blocks
[4:30]
Focus and Dilution: The Multi-stage Learning Process of Attention
[4:45]
Which Algorithms Can Graph Neural Networks Learn?
(ends 5:00 PM)
5 p.m.
Posters 5:00-6:45
Group Cognition Learning: Making Everything Better Through Controlled Two-Stage Agents Collaboration
MOOSE-Star: Unlocking Tractable Training for Scientific Discovery by Breaking the Complexity Barrier
PixCLIP: Towards Fine-grained Vision-Language Understanding via Any-granularity Pixel-Text Alignment
Beyond Independent Genes: Learning Module-Inductive Representations for Gene Perturbation Prediction
Forgetting Whenever You Want: A Decentralized Continual Learning Framework with On-Demand Unlearning
Exploring More to Solve More: Boosting Diversity in Text Diffusion Models via Entropy-Based Guidance
Addressing Semantic Blind Spots in Text-to-SQL via Component Pre-generation and AST Matching Rewards
A Unified Approach to Interpreting Knowledge Distillation for Large Language Models via Interactions
SAGE: A Dataflow-Native Framework for Modular, Controllable, and Transparent LLM-Augmented Reasoning
How Out-of-Distribution Detection Learning Theory Enhances Transformer: Learnability and Reliability
(ends 6:45 PM)
7 p.m.
FRI 10 JUL
7:30 a.m.
(ends 4:00 PM)
8 a.m.
Workshop:
(ends 5:00 PM)
Workshop:
(ends 5:00 PM)
Workshop:
(ends 5:00 PM)
Workshop:
(ends 5:00 PM)
Workshop:
(ends 5:00 PM)
Workshop:
(ends 5:00 PM)
Workshop:
(ends 5:00 PM)
9 a.m.
noon
3 p.m.
SAT 11 JUL
7:30 a.m.
(ends 12:00 PM)
8 a.m.
Workshop:
(ends 5:00 PM)
Workshop:
(ends 5:00 PM)
Workshop:
(ends 5:00 PM)
Workshop:
(ends 5:00 PM)
Workshop:
(ends 5:00 PM)
Workshop:
(ends 5:00 PM)
9 a.m.
noon
3 p.m.
Successful Page Load