MMODELYST
People/Qi Cao
PPL

Qi Cao

Papers (3)
AIBuildAI-2: A Knowledge-Enhanced Agent for Automatically Building AI ModelsLLMs Know When They Know, but Do Not Act on It: A Metacognitive Harness for Test-time ScalingWhy Do Aligned LLMs Remain Jailbreakable: Refusal-Escape Directions, Operator-Level Sources, and Safety-Utility Trade-off