Theory

A Unified Framework for Learning with Nonlinear Model Classes from Arbitrary Linear Samples ICML 2024 Back to the Continuous Attractor NeurIPS 2024 Bagging Provides Assumption-free Stability JMLR 2024 Balancing Context Length and Mixing Times for Reinforcement Learning at Scale NeurIPS 2024 Base of RoPE Bounds Context Length NeurIPS 2024 Batch Normalization Is Blind to the First and Second Derivatives of the Loss AAAI 2024 Batch normalization is sufficient for universal function approximation in CNNs ICLR 2024 Bayes-optimal learning of an extensive-width neural network from quadratically many samples NeurIPS 2024 Benchmarking Counterfactual Image Generation NeurIPS 2024 Benchmarking the Robustness of Temporal Action Detection Models Against Temporal Corruptions CVPR 2024 BerfScene: Bev-conditioned Equivariant Radiance Fields for Infinite 3D Scene Generation CVPR 2024 Best-of-Both-Worlds Algorithms for Linear Contextual Bandits AISTATS 2024 BetterBench: Assessing AI Benchmarks, Uncovering Issues, and Establishing Best Practices NeurIPS 2024 Better-than-KL PAC-Bayes Bounds COLT 2024 Beyond Classification: Definition and Density-Based Estimation of Calibration in Object Detection WACV 2024 Beyond Memorization: The Challenge of Random Memory Access in Language Models ACL 2024 Beyond Optimism: Exploration With Partially Observable Rewards NeurIPS 2024 Beyond Probabilities: Unveiling the Misalignment in Evaluating Large Language Models ACL 2024 Beyond the Calibration Point: Mechanism Comparison in Differential Privacy ICML 2024 Beyond the Numbers: Transparency in Relation Extraction Benchmark Creation and Leaderboards EMNLP 2024 Beyond Vanilla Variational Autoencoders: Detecting Posterior Collapse in Conditional and Hierarchical Variational Autoencoders ICLR 2024 Beyond Weisfeiler-Lehman: A Quantitative Framework for GNN Expressiveness ICLR 2024 Bias in Motion: Theoretical Insights into the Dynamics of Bias in SGD Training NeurIPS 2024 Binary Search with Distributional Predictions NeurIPS 2024 Binding in hippocampal-entorhinal circuits enables compositionality in cognitive maps NeurIPS 2024