generalization

Improving Generalization in Federated Learning with Highly Heterogeneous Data via Momentum-Based Stochastic Controlled Weight Averaging ICML 2025 Improving Generalization with Flat Hilbert Bayesian Inference ICML 2025 Improving Reward Model Generalization from Adversarial Process Enhanced Preferences ICML 2025 Investigating the Overlooked Hessian Structure: From CNNs to LLMs ICML 2025 Learning from Loss Landscape: Generalizable Mixed-Precision Quantization via Adaptive Sharpness-Aware Gradient Aligning ICML 2025 LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently ICML 2025 ManiFlow: A General Robot Manipulation Policy via Consistency Flow Training CoRL 2025 Maximizing Intermediate Checkpoint Value in LLM Pretraining with Bayesian Optimization ICML 2025 Mirror, Mirror of the Flow: How Does Regularization Shape Implicit Bias? ICML 2025 Multi-Loco: Unifying Multi-Embodiment Legged Locomotion via Reinforcement Learning Augmented Diffusion CoRL 2025 Objective drives the consistency of representational similarity across datasets ICML 2025 On the Role of Label Noise in the Feature Learning Process ICML 2025 Orthogonal Subspace Decomposition for Generalizable AI-Generated Image Detection ICML 2025 PEAKS: Selecting Key Training Examples Incrementally via Prediction Error Anchored by Kernel Similarity ICML 2025 Position: General Intelligence Requires Reward-based Pretraining ICML 2025 Position: Graph Matching Systems Deserve Better Benchmarks ICML 2025 Position: LLMs Need a Bayesian Meta-Reasoning Framework for More Robust and Generalizable Reasoning ICML 2025 Position: Rethinking LLM Bias Probing Using Lessons from the Social Sciences ICML 2025 PRIME: Deep Imbalanced Regression with Proxies ICML 2025 Random Registers for Cross-Domain Few-Shot Learning ICML 2025 Reidentify: Context-Aware Identity Generation for Contextual Multi-Agent Reinforcement Learning ICML 2025 Representations Shape Weak-to-Strong Generalization: Theoretical Insights and Empirical Predictions ICML 2025 Right Time to Learn: Promoting Generalization via Bio-inspired Spacing Effect in Knowledge Distillation ICML 2025 Robust Dexterous Grasping of General Objects CoRL 2025 SAFE: Finding Sparse and Flat Minima to Improve Pruning ICML 2025