Across numerical, categorical, and report-generation metrics, the proposed framework substantially improved direct frozen-VLM inference and achieved the strongest overall performance among the evaluated methods, supporting the context-fusion framework as a lightweight and effective strategy for specialist adaptation of...
Rui-Jie Yang, Yan Zhu, Pei-Yao Fu et al.· 0 citations
EndoCLIP, a colonoscopy vision-language foundation model trained on 125,756 lesion-level image-text pairs progressively recovered from 280,476 routine colonoscopy records, is developed, suggesting that recovering finding-to-frame correspondence can transform routine documentation into scalable supervision, enabling cli...
Jia Yu, Yan Zhu, Yili He et al.· arXiv.org· 0 citations
Through rigorous mechanistic analysis, this work identifies the Ghost Anchor phenomenon: a temporal modality asynchrony where linguistic translation to the English semantic manifold completes in early layers, while visual semanticization remains immature.
Yihang Du, Juhao Liang, Zheng-Zhao Lai et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
