moonshotai/Kimi-VL-A3B-Thinking-2506 Image-Text-to-Text • 16B • Updated 4 days ago • 23.3k • 161
Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning Paper • 2506.01939 • Published 29 days ago • 165
ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models Paper • 2505.24864 • Published May 30 • 132
ZeroGUI: Automating Online GUI Learning at Zero Human Cost Paper • 2505.23762 • Published May 29 • 46
ScienceBoard: Evaluating Multimodal Autonomous Agents in Realistic Scientific Workflows Paper • 2505.19897 • Published May 26 • 102