T2R-bench: A Benchmark for Generating Article-Level Reports from Real World Industrial Tables Paper • 2508.19813 • Published Aug 27 • 25
From Captions to Rewards (CAREVL): Leveraging Large Language Model Experts for Enhanced Reward Modeling in Large Vision-Language Models Paper • 2503.06260 • Published Mar 8
Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning Paper • 2506.01939 • Published Jun 2 • 185
Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning Paper • 2506.01939 • Published Jun 2 • 185
Demons in the Detail: On Implementing Load Balancing Loss for Training Specialized Mixture-of-Expert Models Paper • 2501.11873 • Published Jan 21 • 66