Representation Learning

On the Expressive Power of Spectral Invariant Graph Neural Networks ICML 2024 On the Faithfulness of Vision Transformer Explanations CVPR 2024 On the Identifiability of Hybrid Deep Generative Models: Meta-Learning as a Solution NeurIPS 2024 On the Identifiability of Quantized Factors CLeaR 2024 On the Impact of Feature Heterophily on Link Prediction with Graph Neural Networks NeurIPS 2024 On the Intrinsic Structures of Spiking Neural Networks JMLR 2024 On the Joint Interaction of Models, Data, and Features ICLR 2024 On the Multilingual Ability of Decoder-based Pre-trained Language Models: Finding and Controlling Language-Specific Neurons NAACL 2024 On the Nonlinearity of Layer Normalization ICML 2024 On the Nyström Approximation for Preconditioning in Kernel Machines AISTATS 2024 On the Origins of Linear Representations in Large Language Models ICML 2024 On the Over-Memorization During Natural, Robust and Catastrophic Overfitting ICLR 2024 On the Power of Decision Trees in Auto-Regressive Language Modeling NeurIPS 2024 On the Relationship Between RNN Hidden-State Vectors and Semantic Structures ACL 2024 On the Role of Context in Reading Time Prediction EMNLP 2024 On the Stability of Expressive Positional Encodings for Graphs ICLR 2024 On the token distance modeling ability of higher RoPE attention dimension EMNLP 2024 On the Universality of Volume-Preserving and Coupling-Based Normalizing Flows ICML 2024 On the Use of Anchoring for Training Vision Models NeurIPS 2024 OOD Aware Supervised Contrastive Learning WACV 2024 OPEL: Optimal Transport Guided ProcedurE Learning NeurIPS 2024 Operator learning without the adjoint JMLR 2024 Optimal criterion for feature learning of two-layer linear neural network in high dimensional interpolation regime ICLR 2024 Optimal Sample Complexity of Contrastive Learning ICLR 2024 Optimal Transport-based Labor-free Text Prompt Modeling for Sketch Re-identification NeurIPS 2024