T2R-bench: A Benchmark for Generating Article-Level Reports from Real World Industrial Tables Paper • 2508.19813 • Published 11 days ago • 21
MiCRo: Mixture Modeling and Context-aware Routing for Personalized Preference Learning Paper • 2505.24846 • Published May 30 • 15
Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning Paper • 2506.01939 • Published Jun 2 • 180