collaborators

7 papers

cs.LG2026

Understanding and Preserving Safety in Fine-Tuned LLMs

Jiawen Zhang, Yangfan Hu, Kejia Chen +7

Fine-tuning is an essential and pervasive functionality for applying large language models (LLMs) to downstream tasks. However, it has the potential to substantially degrade safety…

cs.LG2026

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

Jiawen Zhang, Lipeng He, Kejia Chen +4

Fine-tuning safety-aligned large language models (LLMs) can substantially compromise their safety. Previous approaches require many safety samples or calibration sets, which not on…

cs.CV2025

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

Kejia Chen, Jiawen Zhang, Jiacong Hu +4

Vision-Language Models (VLMs) have become essential backbones of modern multimodal intelligence, yet their outputs remain prone to hallucination-plausible text misaligned with visu…

cs.LG2025

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

Kejia Chen, Jiawen Zhang, Jiacong Hu +4

Quantized large language models (LLMs) have gained increasing attention and significance for enabling deployment in resource-constrained environments. However, emerging studies on…

cs.CV2025

SHAPE : Self-Improved Visual Preference Alignment by Iteratively Generating Holistic Winner

Kejia Chen, Jiawen Zhang, Jiacong Hu +4

Large Visual Language Models (LVLMs) increasingly rely on preference alignment to ensure reliability, which steers the model behavior via preference fine-tuning on preference data…

cs.CR2025

SecPE: Secure Prompt Ensembling for Private and Robust Large Language Models

Jiawen Zhang, Kejia Chen, Zunlei Feng +4

With the growing popularity of LLMs among the general public users, privacy-preserving and adversarial robustness have become two pressing demands for LLM-based services, which hav…