Xiaojian Li

Scaling reasoning and pretraining loss does not buy self-awareness: top models beat human averages overall yet still fail markedly at metacognition, proving awareness is an independent capability axis.

Multi-turn jailbreak attacks reveal that framing requests as actionable can significantly reduce model vulnerability, highlighting a critical leverage point in AI safety.

Achieve autonomous laparoscope control by translating multimodal surgical data into a single "wrench" that guides the robot's movements.