AI RESEARCH
MedHorizon: Towards Long-context Medical Video Understanding in the Wild
arXiv CS.CV
•
ArXi:2605.06537v1 Announce Type: new Medical multimodal large language models (MLLMs) have advanced image understanding and short-video analysis, but real clinical review often requires full-procedure video understanding. Unlike general long videos, medical procedures contain highly redundant anatomical views, while decisive evidence is temporally sparse, spatially subtle, and context dependent. Existing benchmarks often assume this evidence has already been localized through images, short clips, or pre-segmented videos, leaving the retrieval-before-reasoning problem under-tested. We.