4 papers
OmniSafeBench-MM: A Unified Benchmark and Toolbox for Multimodal Jailbreak Attack-Defense Evaluation
Xiaojun Jia, Jie Liao, Qi Guo +11
Recent advances in multi-modal large language models (MLLMs) have enabled unified perception-reasoning capabilities, yet these systems remain highly vulnerable to jailbreak attacks…
Generative Adversarial Post-Training Mitigates Reward Hacking in Live Human-AI Music Interaction
Yusong Wu, Stephen Brade, Aleksandra Teng Ma +6
Most applications of generative AI involve a sequential interaction in which a person inputs a prompt and waits for a response, and where reaction time and adaptivity are not impor…
EcoAlign: An Economically Rational Framework for Efficient LVLM Alignment
Ruoxi Cheng, Haoxuan Ma, Teng Ma +1
Large Vision-Language Models (LVLMs) exhibit powerful reasoning capabilities but suffer sophisticated jailbreak vulnerabilities. Fundamentally, aligning LVLMs is not just a safety…
Linguistic Calibration of Long-Form Generations
Neil Band, Xuechen Li, Tengyu Ma +1
Language models (LMs) may lead their users to make suboptimal downstream decisions when they confidently hallucinate. This issue can be mitigated by having the LM verbally convey t…