"au:"Jinhu Fu"" — arXiv2 Search

/ Date/ Name

/ Date/ Name

"au:"Jinhu Fu"" — arXiv2 Search

Showing 1–4 of 4 results

/ Date/ Name

Mar 28, 2026Diagnosing and Repairing Unsafe Channels in Vision-Language Models via Causal Discovery and Dual-Modal Safety Subspace Projection Apr 7, 2026Learning to Edit Knowledge via Instruction-based Chain-of-Thought Prompting Apr 22, 2025A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment Apr 20, 2025REDEditing: Relationship-Driven Precise Backdoor Poisoning on Text-to-Image Diffusion Models