Yihao Li

This paper formalizes the binding problem using information theory and develops a probing method to measure binding information in deep learning representations, demonstrating that binding is crucial for strong visual recognition.

The paper proposes Skill-RM, a unified framework that treats reward modeling as an agentic task to consistently integrate diverse evaluation criteria, achieving superior performance over traditional methods.

This paper introduces Skill Self-Play (Skill-SP), a co-evolutionary framework for LLM training that bridges the gap between structured verification and open-ended exploration.