2026

论文总结-Safevla:Towards safety alignment of vision-language-action model via constrained learning 04-03 论文总结- VLMGuard-R1:Proactive Safety Alignment for VLMs via Reasoning-Driven Prompt Optimization 04-02 论文总结-HoliSafe:Holistic Safety Benchmarking and Modeling for Vision-Language Model 03-31 论文总结-MMJ-Bench:A Comprehensive Study on Jailbreak Attacks and Defenses for Vision Language Models 03-13 论文总结-Instruction-Following Evaluation for Large Language Models 03-12 论文总结-AGENTIF:Benchmarking Instruction Following of Large Language Models in Agentic Scenarios 03-12