InCoder-32B-Thinking: Industrial Code World Model for Thinking Paper • 2604.03144 • Published 16 days ago • 231
HopChain: Multi-Hop Data Synthesis for Generalizable Vision-Language Reasoning Paper • 2603.17024 • Published Mar 17 • 109
Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning Paper • 2506.01939 • Published Jun 2, 2025 • 190