Theory

On the Trainability and Classical Simulability of Learning Matrix Product States Variationally AAAI 2025 On Tradeoffs in Learning-Augmented Algorithms AISTATS 2025 Optimal Brain Apoptosis ICLR 2025 Optimal Learning of Kernel Logistic Regression for Complex Classification Scenarios ICLR 2025 Orthogonal Bases for Equivariant Graph Learning with Provable k-WL Expressive Power JMLR 2025 Paradigms of AI Evaluation: Mapping Goals, Methodologies and Culture IJCAI 2025 Parallel Belief Revision via Order Aggregation IJCAI 2025 Parameterized Complexity of Caching in Networks AAAI 2025 Paraphrase Generation Evaluation Powered by an LLM: A Semantic Metric, Not a Lexical One COLING 2025 Partial Identifiability in Inverse Reinforcement Learning for Agents with Non-Exponential Discounting AAAI 2025 Patterns Over Principles: The Fragility of Inductive Reasoning in LLMs under Noisy Observations ACL 2025 Physics-Informed Deep Learning and Compressive Collocation for High-Dimensional Diffusion-Reaction Equations: Practical Existence Theory and Numerics JMLR 2025 PIG: Physics-Informed Gaussians as Adaptive Parametric Mesh Representations ICLR 2025 PIN: Prolate Spheroidal Wave Function-based Implicit Neural Representations ICLR 2025 PlanGenLLMs: A Modern Survey of LLM Planning Capabilities ACL 2025 p-Mean Regret for Stochastic Bandits AAAI 2025 Poisson-Dirac Neural Networks for Modeling Coupled Dynamical Systems across Domains ICLR 2025 Polynomial Composition Activations: Unleashing the Dynamics of Large Language Models ICLR 2025 Polynomial-Time Relational Probabilistic Inference in Open Universes IJCAI 2025 PolyPythias: Stability and Outliers across Fifty Language Model Pre-Training Runs ICLR 2025 Positional Attention: Expressivity and Learnability of Algorithmic Computation ICML 2025 PoWER Never Corrupts: Tool-Agnostic Verification of Crash Consistency and Corruption Detection OSDI 2025 Prediction Hubs are Context-Informed Frequent Tokens in LLMs ACL 2025 PREMAP: A Unifying PREiMage APproximation Framework for Neural Networks JMLR 2025 Privacy Auditing of Large Language Models ICLR 2025