4 papers
Mitigating Action-Relation Hallucinations in LVLMs via Relation-aware Visual Enhancement
Zhenxin Qin, Qiang Li, Qingzhuo Wang +3
Large Vision-Language Models (LVLMs) have achieved remarkable performance on diverse vision-language tasks. However, LVLMs still suffer from hallucinations, generating text that co…
Multilingual Safety Alignment via Self-Distillation
Ruiyang Qin, Qingzhuo Wang, Dongrui Liu +3
Large language models (LLMs) exhibit severe multilingual safety misalignment: they possess strong safeguards in high-resource languages but remain highly vulnerable to jailbreak at…
LoopVLA: Learning Sufficiency in Recurrent Refinement for Vision-Language-Action Models
Boyang Shen, Kaixiang Yang, Hao Wang +4
Current Vision-Language-Action (VLA) models typically treat the deepest representation of a vision-language backbone as universally optimal for action prediction. However, robotic…
Understanding and Defending VLM Jailbreaks via Jailbreak-Related Representation Shift
Zhihua Wei, Qiang Li, Jian Ruan +6
Large vision-language models (VLMs) often exhibit weakened safety alignment with the integration of the visual modality. Even when text prompts contain explicit harmful intent, add…