Xianjun Yang

Verifying Chain-of-Thought Reasoning via Its Computational Graph

Your thoughts tell who you are: Characterize the reasoning patterns of LRMs

Beyond Reasoning Gains: Mitigating General Capabilities Forgetting in Large Reasoning Model

Weak-to-Strong Jailbreaking on Large Language Models

MMSci: A Dataset for Graduate-Level Multi-Discipline Multimodal Scientific Understanding

Weak-to-Strong Jailbreaking on Large Language Models

Test-Time Backdoor Attacks on Multimodal Large Language Models

MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents