Xiaomin Li

The paper investigates multimodal jailbreak robustness across various reasoning paradigms and finds that explicit image-tool interaction significantly improves safety by guiding the model's internal representations toward safer directions.

The paper investigates multimodal jailbreak robustness across various reasoning paradigms and finds that explicit image-tool interaction significantly improves safety by shifting the model's internal representations toward a safety-relevant direction.

The paper introduces FAM-Bench, a novel multimodal benchmark designed to test advanced, condition-aware reasoning for food-as-medicine applications.

This paper proposes TRIAGE, a role-typed credit assignment framework for agentic reinforcement learning to address the structural incompleteness of standard GRPO.