AI.info

Ruizhe Li

Explore Ruizhe Li on AI.info.

• Locked at the Entrance, Open Inside: Where RLVR Narrows the Solution Space
• Orthogonal Hierarchical Decomposition for Structure-Aware Table Understanding with Large Language Models
• Tracing the Latent Threads: A Mechanistic Study of How LLMs Represent and Operationalize Race and Ethnicity Cues
• Spurious Rewards Paradox: Mechanistically Understanding How RLVR Activates Memorization Shortcuts in LLMs