Zhong-Zhi Li

3 papers Institute of automation, Chinese academy of science, Chinese Academy of Sciences

• PeRL: Permutation-Enhanced Reinforcement Learning for Interleaved Vision-Language Reasoning
• SolidGeo: Measuring Multimodal Spatial Math Reasoning in Solid Geometry
• SwS: Self-aware Weakness-driven Problem Synthesis in Reinforcement Learning for LLM Reasoning