WildRelight: A Real-World Benchmark and Physics-Guided Adaptation for Single-Image Relighting Paper • 2605.11696 • Published 4 days ago • 3
Beyond Accuracy: Unveiling Inefficiency Patterns in Tool-Integrated Reasoning Paper • 2604.05404 • Published Apr 7 • 42
ACES: Who Tests the Tests? Leave-One-Out AUC Consistency for Code Generation Paper • 2604.03922 • Published Apr 5 • 53
DataFlex: A Unified Framework for Data-Centric Dynamic Training of Large Language Models Paper • 2603.26164 • Published Mar 27 • 364
Adam's Law: Textual Frequency Law on Large Language Models Paper • 2604.02176 • Published Apr 2 • 503