Tanqiu Jiang

Cross-Modal Content Optimization for Steering Web Agent Preferences

AutoRAN: Automated Hijacking of Safety Reasoning in Large Reasoning Models

Self-Improving Model Steering

Safeguarding Vision-Language Models via Dynamic Token Reweighting

RobustKV: Defending Large Language Models against Jailbreak Attacks via KV Eviction

RAPID: Retrieval Augmented Training of Differentially Private Diffusion Models