Showing cs.CVShow all
2 papers · 1 filter
cs.CV2026
Beyond Language Priors: Diagnosing and Fixing Visual-Origin Hallucinations in Multimodal LLM
Peiyang Xu, Xiaopei Zhu, Jun Zhu +1
Existing research on object hallucination in multimodal large language models (MLLMs) predominantly attributes the problem to language priors such as over-reliance on textual co-oc…
cs.CV2025
SafeVision: Efficient Image Guardrail with Robust Policy Adherence and Explainability
Peiyang Xu, Minzhou Pan, Zhaorun Chen +3
With the rapid proliferation of digital media, the need for efficient and transparent safeguards against unsafe content is more critical than ever. Traditional image guardrail mode…