Learning Theory

Best-Arm Identification in Unimodal Bandits AISTATS 2025 Best of Both Worlds: Regret Minimization versus Minimax Play ICML 2025 Better Private Distribution Testing by Leveraging Unverified Auxiliary Data COLT 2025 Beyond Log-Concavity and Score Regularity: Improved Convergence Bounds for Score-Based Generative Models in W2-distance ICML 2025 Beyond Losses Reweighting: Empowering Multi-Task Learning via the Generalization Perspective ICCV 2025 Beyond Memorization: Assessing Semantic Generalization in Large Language Models Using Phrasal Constructions IJCNLP 2025 Beyond Single-Value Metrics: Evaluating and Enhancing LLM Unlearning with Cognitive Diagnosis ACL 2025 Beyond Surprisal: A Dual Metric Framework for Lexical Skill Acquisition in LLMs COLING 2025 Beyond the Leaderboard: Understanding Performance Disparities in Large Language Models via Model Diffing EMNLP 2025 Beyond Worst-Case Online Classification: VC-Based Regret Bounds for Relaxed Benchmarks COLT 2025 Black-Box Uniform Stability for Non-Euclidean Empirical Risk Minimization AISTATS 2025 Boosting Adversarial Robustness with CLAT: Criticality Leveraged Adversarial Training ICML 2025 Boosting Causal Additive Models JMLR 2025 Boosting, Voting Classifiers and Randomized Sample Compression Schemes ALT 2025 Breaking Neural Network Scaling Laws with Modularity ICLR 2025 Bridging Fairness and Efficiency in Conformal Inference: A Surrogate-Assisted Group-Clustered Approach ICML 2025 Bypassing LLM Guardrails: An Empirical Analysis of Evasion Attacks against Prompt Injection and Jailbreak Detection Systems ACL 2025 C2IQL: Constraint-Conditioned Implicit Q-learning for Safe Offline Reinforcement Learning ICML 2025 Calibrated Value-Aware Model Learning with Probabilistic Environment Models ICML 2025 Can In-context Learning Really Generalize to Out-of-distribution Tasks? ICLR 2025 Can Large Language Models Win the International Mathematical Games? EMNLP 2025 Can LLMs Reason About Program Semantics? A Comprehensive Evaluation of LLMs on Formal Specification Inference ACL 2025 Can Neural Networks Achieve Optimal Computational-statistical Tradeoff? An Analysis on Single-Index Model ICLR 2025 Can Out-of-Distribution Evaluations Uncover Reliance on Prediction Shortcuts? A Case Study in Question Answering EMNLP 2025 Can RLHF be More Efficient with Imperfect Reward Models? A Policy Coverage Perspective ICML 2025