Learning Theory

U-shaped and Inverted-U Scaling behind Emergent Abilities of Large Language Models ICLR 2025 Validating Mechanistic Interpretations: An Axiomatic Approach ICML 2025 Variance-Dependent Regret Bounds for Nonstationary Linear Bandits AISTATS 2025 Variance Sensitivity Induces Attention Entropy Collapse and Instability in Transformers EMNLP 2025 Veracity Bias and Beyond: Uncovering LLMs’ Hidden Beliefs in Problem-Solving Reasoning ACL 2025 VideoVista-CulturalLingo: 360° Horizons-Bridging Cultures, Languages, and Domains in Video Comprehension ACL 2025 Weak-to-Strong Generalization Even in Random Feature Networks, Provably ICML 2025 Weak-to-Strong Generalization Through the Data-Centric Lens ICLR 2025 Weak to Strong Learning from Aggregate Labels UAI 2025 What Did I Do Wrong? Quantifying LLMs’ Sensitivity and Consistency to Prompt Engineering NAACL 2025 What Do Learning Dynamics Reveal About Generalization in LLM Mathematical Reasoning? ICML 2025 What Makes In-context Learning Effective for Mathematical Reasoning ICML 2025 When can in-context learning generalize out of task distribution? ICML 2025 When Can Proxies Improve the Sample Complexity of Preference Learning? ICML 2025 When Can We Approximate Wide Contrastive Models with Neural Tangent Kernels and Principal Component Analysis? AAAI 2025 When does compositional structure yield compositional generalization? A kernel theory. ICLR 2025 When do neural networks learn world models? ICML 2025 When Dynamic Data Selection Meets Data Augmentation: Achieving Enhanced Training Acceleration ICML 2025 When narrower is better: the narrow width limit of Bayesian parallel branching neural networks ICLR 2025 When Should Dense Retrievers Be Updated in Evolving Corpora? Detecting Out-of-Distribution Corpora Using GradNormIR ACL 2025 Where is the answer? An empirical study of positional bias for parametric knowledge extraction in language model NAACL 2025 Which Word Orders Facilitate Length Generalization in LMs? An Investigation with GCG-Based Artificial Languages EMNLP 2025 Whoever Started the interference Should End It: Guiding Data-Free Model Merging via Task Vectors ICML 2025 Why do language models perform worse for morphologically complex languages? COLING 2025 Why Has Predicting Downstream Capabilities of Frontier AI Models with Scale Remained Elusive? ICML 2025