7 papers
HeadHunt-VAD: Hunting Robust Anomaly-Sensitive Heads in MLLM for Tuning-Free Video Anomaly Detection
Zhaolin Cai, Fan Li, Ziwei Zheng +2
Video Anomaly Detection (VAD) aims to locate events that deviate from normal patterns in videos. Traditional approaches often rely on extensive labeled data and incur high computat…
HiProbe-VAD: Video Anomaly Detection via Hidden States Probing in Tuning-Free Multimodal LLMs
Zhaolin Cai, Fan Li, Ziwei Zheng +1
Video Anomaly Detection (VAD) aims to identify and locate deviations from normal patterns in video sequences. Traditional methods often struggle with substantial computational dema…
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…
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…
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…
Nullu: Mitigating Object Hallucinations in Large Vision-Language Models via HalluSpace Projection
Le Yang, Ziwei Zheng, Boxu Chen +3
Recent studies have shown that large vision-language models (LVLMs) often suffer from the issue of object hallucinations (OH). To mitigate this issue, we introduce an efficient met…