Learning Theory

Do Construction Distributions Shape Formal Language Learning In German BabyLMs? CoNLL 2025 Does GPT Really Get It? A Hierarchical Scale to Quantify Human and AI’s Understanding of Algorithms AAAI 2025 Does Graph Prompt Work? A Data Operation Perspective with Theoretical Analysis ICML 2025 Do ImageNet-trained Models Learn Shortcuts? The Impact of Frequency Shortcuts on Generalization CVPR 2025 Do Influence Functions Work on Large Language Models? EMNLP 2025 Do Large Language Models Truly Grasp Addition? A Rule-Focused Diagnostic Using Two-Integer Arithmetic EMNLP 2025 Do LLMs Adhere to Label Definitions? Examining Their Receptivity to External Label Definitions EMNLP 2025 Don’t Take the Premise for Granted: Evaluating the Premise Critique Ability of Large Language Models EMNLP 2025 Do PAC-Learners Learn the Marginal Distribution? ALT 2025 Do We Always Need the Simplicity Bias? Looking for Optimal Inductive Biases in the Wild CVPR 2025 Do We Need to Verify Step by Step? Rethinking Process Supervision from a Theoretical Perspective ICML 2025 Dynamical phases of short-term memory mechanisms in RNNs ICML 2025 Effective Littlestone dimension ALT 2025 Effects of Momentum in Implicit Bias of Gradient Flow for Diagonal Linear Networks AAAI 2025 Efficient Exploitation of Hierarchical Structure in Sparse Reward Reinforcement Learning AISTATS 2025 Efficient Heterogeneity-Aware Federated Active Data Selection ICML 2025 Efficient Optimal PAC Learning ALT 2025 Efficient PAC Learning of Halfspaces with Constant Malicious Noise Rate ALT 2025 Efficient Training of Neural Stochastic Differential Equations by Matching Finite Dimensional Distributions ICLR 2025 Ehrenfeucht-Haussler Rank and Chain of Thought ICML 2025 Eigen Analysis of Conjugate Kernel and Neural Tangent Kernel ICML 2025 End-to-End Learning Framework for Solving Non-Markovian Optimal Control ICML 2025 Enhanced H-Consistency Bounds ALT 2025 Enhancing Adversarial Robustness with Conformal Prediction: A Framework for Guaranteed Model Reliability ICML 2025 Enhancing Diversity In Parallel Agents: A Maximum State Entropy Exploration Story ICML 2025