most citedMitigating Hallucination in Visual Language Models with Visual Supervision

2 citations · 2 across the 4 of their papers we have counts for

collaborators
Showing cs.CVShow all

2 papers · 1 filter

cs.CV2026

UniVAD v2: Unified Visual Anomaly Detection via Support-Conditioned Boundary Construction

Zhaopeng Gu, Bingke Zhu, Zhaowen Li +5

Unified visual anomaly detection seeks to train a single detector that can be deployed across categories, domains, and application scenarios. In the few-shot transfer regime, the k…

cs.CV2023★ 2 cited

Mitigating Hallucination in Visual Language Models with Visual Supervision

Zhiyang Chen, Yousong Zhu, Yufei Zhan +4

Large vision-language models (LVLMs) suffer from hallucination a lot, generating responses that apparently contradict to the image content occasionally. The key problem lies in its…