Jiawen Zhang

Safety at One Shot: Patching Fine-Tuned LLMs with A Single Instance

CASPO: Confidence-aware Step-wise Preference Optimization for Reliable Reasoning in Large Language Models

ReSaM: Representation-Level Safety Margin Alignment for Vision–Language Models

Token-level Inference-Time Alignment for Vision-Language Models

Assessing Safety Risks and Quantization-aware Safety Patching for Quantized Large Language Models

Q-resafe: Assessing Safety Risks and Quantization-aware Safety Patching for Quantized Large Language Models