Theory

Interventional Causal Discovery in a Mixture of DAGs NeurIPS 2024 Interventionally Consistent Surrogates for Complex Simulation Models NeurIPS 2024 Intriguing Properties of Data Attribution on Diffusion Models ICLR 2024 Intrinsic Robustness of Prophet Inequality to Strategic Reward Signaling NeurIPS 2024 Introducing PaVeDa – Pavia Verbs Database: Valency Patterns and Pattern Comparison in Ancient Indo-European Languages COLING 2024 Invariant Physics-Informed Neural Networks for Ordinary Differential Equations JMLR 2024 Inverse Approximation Theory for Nonlinear Recurrent Neural Networks ICLR 2024 Inverse M-Kernels for Linear Universal Approximators of Non-Negative Functions NeurIPS 2024 Investigating Data Contamination in Modern Benchmarks for Large Language Models NAACL 2024 Is Behavior Cloning All You Need? Understanding Horizon in Imitation Learning NeurIPS 2024 Is Efficient PAC Learning Possible with an Oracle That Responds "Yes" or "No"? COLT 2024 Isotropy, Clusters, and Classifiers ACL 2024 It Ain’t That Bad: Understanding the Mysterious Performance Drop in OOD Generalization for Generative Transformer Models IJCAI 2024 Item Response Theory for Natural Language Processing EACL 2024 It’s Not Easy Being Wrong: Large Language Models Struggle with Process of Elimination Reasoning ACL 2024 JoMA: Demystifying Multilayer Transformers via Joint Dynamics of MLP and Attention ICLR 2024 Keyphrase Generation: Lessons from a Reproducibility Study COLING 2024 Koopman-based generalization bound: New aspect for full-rank weights ICLR 2024 Language Generation in the Limit NeurIPS 2024 Language Models as Zero-shot Lossless Gradient Compressors: Towards General Neural Parameter Prior Models NeurIPS 2024 Language Models Do Hard Arithmetic Tasks Easily and Hardly Do Easy Arithmetic Tasks ACL 2024 Large Stepsize Gradient Descent for Non-Homogeneous Two-Layer Networks: Margin Improvement and Fast Optimization NeurIPS 2024 LeanReasoner: Boosting Complex Logical Reasoning with Lean NAACL 2024 Learnability of Linear Port-Hamiltonian Systems JMLR 2024 Learned Transformer Position Embeddings Have a Low-Dimensional Structure ACL 2024