Zeyang Sha

Teach to Reason Safely: Policy-Guided Safety Tuning for MLRMs

The Reasoning Trap: How Enhancing LLM Reasoning Amplifies Tool Hallucination

InjecMEM: Memory Injection Attack on LLM Agent Memory Systems

SEM: Reinforcement Learning For Search-Efficient Large Language Models

Fine-Tuning Is All You Need to Mitigate Backdoor Attacks