Learning Theory

Learning with Exact Invariances in Polynomial Time ICML 2025 Learning with Linear Function Approximations in Mean-Field Control JMLR 2025 Learning With Multi-Group Guarantees For Clusterable Subpopulations ICML 2025 Lemmas Matter, But Not Like That: Predictors of Lemma-Based Generalization in Morphological Inflection ACL 2025 LensLLM: Unveiling Fine-Tuning Dynamics for LLM Selection ICML 2025 Let Me Grok for You: Accelerating Grokking via Embedding Transfer from a Weaker Model ICLR 2025 Leveraging Per-Instance Privacy for Machine Unlearning ICML 2025 Leveraging Randomness in Model and Data Partitioning for Privacy Amplification ICML 2025 Lexical Recall or Logical Reasoning: Probing the Limits of Reasoning Abilities in Large Language Models ACL 2025 Lexicographic Lipschitz Bandits: New Algorithms and a Lower Bound JMLR 2025 LiBOG: Lifelong Learning for Black-Box Optimizer Generation IJCAI 2025 LibraGrad: Balancing Gradient Flow for Universally Better Vision Transformer Attributions CVPR 2025 Limited Generalizability in Argument Mining: State-Of-The-Art Models Learn Datasets, Not Arguments ACL 2025 Limits to scalable evaluation at the frontier: LLM as judge won’t beat twice the data ICLR 2025 Linear Convergence of Diffusion Models Under the Manifold Hypothesis COLT 2025 Linear Streaming Bandit: Regret Minimization and Fixed-Budget Epsilon-Best Arm Identification AAAI 2025 LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code ICLR 2025 LLMs cannot spot math errors, even when allowed to peek into the solution EMNLP 2025 LLM The Genius Paradox: A Linguistic and Math Expert’s Struggle with Simple Word-based Counting Problems NAACL 2025 Local Regularizers Are Not Transductive Learners COLT 2025 Logarithmic Regret for Linear Markov Decision Processes with Adversarial Corruptions AAAI 2025 Logarithmic Regret for Nonlinear Control L4DC 2025 Logarithmic Width Suffices for Robust Memorization COLT 2025 LogiDynamics: Unraveling the Dynamics of Inductive, Abductive and Deductive Logical Inferences in LLM Reasoning EMNLP 2025 LogRules: Enhancing Log Analysis Capability of Large Language Models through Rules NAACL 2025