Toggle Poster Visibility
Fri Jul 23 06:15 AM -- 06:45 AM (PDT)
Uncertainty Modeling from 50M to 1B
Fri Jul 23 06:45 AM -- 08:00 AM (PDT)
Live Poster session #1 (Europe/Asia friendly)
Fri Jul 23 08:15 AM -- 08:45 AM (PDT)
Some Thoughts on Generalization, Robustness, and their application with CLIP
Fri Jul 23 08:45 AM -- 10:00 AM (PDT)
Live Poster session #2 (America friendly)
Fri Jul 23 10:00 AM -- 10:45 AM (PDT)
Live Panel Discussion
Fri Jul 23 11:15 AM -- 11:25 AM (PDT)
Repulsive Deep Ensembles are Bayesian
Fri Jul 23 11:25 AM -- 11:35 AM (PDT)
Wide Mean-Field Variational Bayesian Neural Networks Ignore the Data
Fri Jul 23 11:35 AM -- 11:45 AM (PDT)
Are Bayesian neural networks intrinsically good at out-of-distribution detection?
Fri Jul 23 11:45 AM -- 12:15 PM (PDT)
Improving Robustness to Distribution Shifts: Methods and Benchmarks
Fri Jul 23 12:30 PM -- 01:00 PM (PDT)
Evaluating deep learning models with applications to NLP
Fri Jul 23 01:00 PM -- 01:10 PM (PDT)
Calibrated Out-of-Distribution Detection with Conformal P-values
Fri Jul 23 01:10 PM -- 01:20 PM (PDT)
Provably Robust Detection of Out-of-distribution Data (almost) for free
Fri Jul 23 01:20 PM -- 01:30 PM (PDT)
Out-of-Distribution Dynamics Detection: RL-Relevant Benchmarks and Results
Fri Jul 23 01:30 PM -- 02:00 PM (PDT)
Contrastive Learning for Novelty Detection
Defending against Adversarial Patches with Robust Self-Attention
Novelty detection using ensembles with regularized disagreement
Stochastic Bouncy Particle Sampler for Bayesian Neural Networks
Improved Adversarial Robustness via Uncertainty Targeted Attacks
Model-Based Robust Deep Learning: Generalizing to Natural, Out-of-Distribution Data
PnPOOD : Out-Of-Distribution Detection for Text Classification via Plug andPlay Data Augmentation
On Pitfalls in OoD Detection: Entropy Considered Harmful
On Misclassification-Aware Smoothing for Robustness and Uncertainty Calibration
Identifying Invariant and Sparse Predictors in High-dimensional Data
Deep Deterministic Uncertainty for Semantic Segmentation
Deep Random Projection Outlyingness for Unsupervised Anomaly Detection
Exploring Corruption Robustness: Inductive Biases in Vision Transformers and MLP-Mixers
Robust Generalization of Quadratic Neural Networks via Function Identification
On the reversed bias-variance tradeoff in deep ensembles
Scaling Laws for the Out-of-Distribution Generalization of Image Classifiers
Deep Learning with Quantified Uncertainty for Free Electron Laser Scientific Facilities
Directly Training Joint Energy-Based Models for Conditional Synthesis and Calibrated Prediction of Multi-Attribute Data
Multi-task Transformation Learning for Robust Out-of-Distribution Detection
Training-Free Uncertainty Estimation for Dense Regression: Sensitivity as a Surrogate
On the Effectiveness of Mode Exploration in Bayesian Model Averaging for Neural Networks
Relational Deep Reinforcement Learning and Latent Goals for Following Instructions in Temporal Logic
On The Dark Side Of Calibration For Modern Neural Networks
Out-of-Distribution Generalization with Deep Equilibrium Models
No True State-of-the-Art? OOD Detection Methods are Inconsistent across Datasets
RouBL: A computationally cheap way to go beyond mean-field variational inference
Uncertainty-Aware Boosted Ensembling in Multi-Modal Settings
What Are Effective Labels for Augmented Data? Improving Calibration and Robustness with AutoLabel
A variational approximate posterior for the deep Wishart process
Contrastive Predictive Coding for Anomaly Detection and Segmentation
Revisiting Out-of-Distribution Detection: A Simple Baseline is Surprisingly Effective
Beyond First-Order Uncertainty Estimation with Evidential Models for Open-World Recognition
How does a Neural Network's Architecture Impact its Robustness to Noisy Labels?
Distribution-free uncertainty quantification for classification under label shift
Towards Stochastic Neural Networks via Inductive Wasserstein Embeddings
Epistemic Uncertainty in Learning Chaotic Dynamical Systems
On the Calibration of Deterministic Epistemic Uncertainty
The Hidden Uncertainty in a Neural Network’s Activations
Accuracy on the Line: on the Strong Correlation Between Out-of-Distribution and In-Distribution Generalization
Evaluating the Use of Reconstruction Error for Novelty Localization
Consistency Regularization Can Improve Robustness to Label Noise
Improving the Accuracy-Robustness Trade-Off for Dual-Domain Adversarial Training
Variational Generative Flows for Reconstruction Uncertainty Estimation
Practical posterior Laplace approximation with optimization-driven second moment estimation
A Bayesian Approach to Invariant Deep Neural Networks
Batch Inverse-Variance Weighting: Deep Heteroscedastic Regression
Anomaly Detection for Event Data with Temporal Point Processes
Class-Distribution-Aware Calibration for Long-Tailed Visual Recognition
Quantization of Bayesian neural networks and its effect on quality of uncertainty
Diverse and Amortised Counterfactual Explanations for Uncertainty Estimates
Exact and Efficient Adversarial Robustness with Decomposable Neural Networks
Deep Ensemble Uncertainty Fails as Network Width Increases: Why, and How to Fix It
Mean Embeddings with Test-Time Data Augmentation for Ensembling of Representations
BETH Dataset: Real Cybersecurity Data for Anomaly Detection Research
Understanding the Under-Coverage Bias in Uncertainty Estimation
Rethinking Function-Space Variational Inference in Bayesian Neural Networks
Safety & Exploration: A Comparative Study of Uses of Uncertainty in Reinforcement Learning
Simple, Attack-Agnostic Defense Against Targeted Training Set Attacks Using Cosine Similarity
SAND-mask: An Enhanced Gradient Masking Strategy for Invariant Prediction in Domain Generalization
Inferring Black Hole Properties from Astronomical Multivariate Time Series with Bayesian Attentive Neural Processes
Transfer and Marginalize: Explaining Away Label Noise with Privileged Information
Meta-Calibration: Meta-Learning of Model Calibration Using Differentiable Expected Calibration Error
Deterministic Neural Networks with Inductive Biases Capture Epistemic and Aleatoric Uncertainty
On Out-of-distribution Detection with Energy-Based Models
Failures of Uncertainty Estimation on Out-Of-Distribution Samples: Experimental Results from Medical Applications Lead to Theoretical Insights
Implicit Ensemble Training for Efficient and Robust Multiagent Reinforcement Learning
Uncertainty Toolbox: an Open-Source Library for Assessing, Visualizing, and Improving Uncertainty Quantification
Beyond Pinball Loss: Quantile Methods for Calibrated Uncertainty Quantification
Do We Really Need to Learn Representations from In-domain Data for Outlier Detection?
Correct-N-Contrast: a Contrastive Approach for Improving Robustness to Spurious Correlations
Out-of-Distribution Dynamics Detection: RL-Relevant Benchmarks and Results
Provably Robust Detection of Out-of-distribution Data (almost) for free
Calibrated Out-of-Distribution Detection with Conformal P-values
Disentangling the Roles of Curation, Data-Augmentation and the Prior in the Cold Posterior Effect
Precise characterization of the prior predictive distribution of deep ReLU networks
Wide Mean-Field Variational Bayesian Neural Networks Ignore the Data
A simple fix to Mahalanobis distance for improving near-OOD detection
Exploring the Limits of Out-of-Distribution Detection
What Are Effective Labels for Augmented Data? Improving Calibration and Robustness with AutoLabel
Are Bayesian neural networks intrinsically good at out-of-distribution detection?
Mixture Proportion Estimation and PU Learning: A Modern Approach
An Empirical Study of Invariant Risk Minimization on Deep Models
Consistency Regularization for Training Confidence-Calibrated Classifiers
DATE: Detecting Anomalies in Text via Self-Supervision of Transformers
Multiple Moment Matching Inference: A Flexible Approximate Inference Algorithm
Relating Adversarially Robust Generalization to Flat Minima
Thinkback: Task-Specific Out-of-Distribution Detection
Analyzing And Improving Neural Networks By Generating Semantic Counterexamples Through Differentiable Rendering
Dataset to Dataspace: A Topological-Framework to Improve Analysis of Machine Learning Model Performance