Similar Items: MedVIGIL: Evaluating Trustworthy Medical VLMs Under Broken Visual Evidence
- GeoStack: A Framework for Quasi-Abelian Knowledge Composition in VLMs
- MedHorizon: Towards Long-context Medical Video Understanding in the Wild
- PubMed-Ophtha: An open resource for training ophthalmology vision-language models on scientific literature
- Representation Fréchet Loss for Visual Generation
- Perceptual Flow Network for Visually Grounded Reasoning
- Audio-Visual Intelligence in Large Foundation Models