Learning Theory

Enhancing Prediction Performance through Influence Measure ICLR 2025 Enhancing the Influence of Labels on Unlabeled Nodes in Graph Convolutional Networks ICML 2025 Enhancing Treatment Effect Estimation via Active Learning: A Counterfactual Covering Perspective ICML 2025 Ensemble Learned Bloom Filters: Two Oracles are Better than One ICML 2025 Equivariant Neural Tangent Kernels ICML 2025 Error Analysis Affected by Heavy-Tailed Gradients for Non-Convex Pairwise Stochastic Gradient Descent AAAI 2025 Evaluating LLMs’ Reasoning Over Ordered Procedural Steps IJCNLP 2025 Evaluating Mathematical Reasoning Beyond Accuracy AAAI 2025 Evaluating Morphological Compositional Generalization in Large Language Models NAACL 2025 Evaluating Numeracy of Language Models as a Natural Language Inference Task NAACL 2025 Evaluating Robustness of LLMs to Numerical Variations in Mathematical Reasoning NAACL 2025 Evaluating Step-by-step Reasoning Traces: A Survey EMNLP 2025 Evaluating the Evaluators: Are readability metrics good measures of readability? EMNLP 2025 Every Bit Helps: Achieving the Optimal Distortion with a Few Queries AAAI 2025 EvoChart: A Benchmark and a Self-Training Approach Towards Real-World Chart Understanding AAAI 2025 Evolutionary Algorithms Are Significantly More Robust to Noise When They Ignore It IJCAI 2025 Exact Algorithms and Lower Bounds for Forming Coalitions of Constrained Maximum Size AAAI 2025 Exact Certification of (Graph) Neural Networks Against Label Poisoning ICLR 2025 Exactly Tight Information-theoretic Generalization Bounds via Binary Jensen-Shannon Divergence ICML 2025 Exact risk curves of signSGD in High-Dimensions: quantifying preconditioning and noise-compression effects ICML 2025 EXECUTE: A Multilingual Benchmark for LLM Token Understanding ACL 2025 Existence of Adversarial Examples for Random Convolutional Networks via Isoperimetric Inequalities on SO(d) COLT 2025 Exploiting Structure in Offline Multi-Agent RL: The Benefits of Low Interaction Rank ICLR 2025 Exploring the Hidden Reasoning Process of Large Language Models by Misleading Them EMNLP 2025 Exploring the Over-smoothing Problem of Graph Neural Networks for Graph Classification: An Entropy-based Viewpoint IJCAI 2025