Showing 2025Show all
3 papers · 1 filter
cs.CV2025
Seeing It or Not? Interpretable Vision-aware Latent Steering to Mitigate Object Hallucinations
Boxu Chen, Ziwei Zheng, Le Yang +4
Large Vision-Language Models (LVLMs) have achieved remarkable success but continue to struggle with object hallucination (OH), generating outputs inconsistent with visual inputs. W…
cs.CV2025
DeepEyes: Incentivizing "Thinking with Images" via Reinforcement Learning
Ziwei Zheng, Michael Yang, Jack Hong +5
Large Vision-Language Models excel at multimodal understanding but struggle to deeply integrate visual information into their predominantly text-based reasoning processes, a key ch…
cs.LG2025
Spot Risks Before Speaking! Unraveling Safety Attention Heads in Large Vision-Language Models
Ziwei Zheng, Junyao Zhao, Le Yang +2
With the integration of an additional modality, large vision-language models (LVLMs) exhibit greater vulnerability to safety risks (e.g., jailbreaking) compared to their language-o…