2 papers
cs.CV2026
MedStreamBench: A Time-Aware Benchmark for Streaming and Proactive Medical Video Understanding
Yuan Wang, Shujian Gao, Songtao Jiang +2
Existing medical video benchmarks primarily evaluate whether a model produces the correct answer, but rarely assess whether it answers at the right time. In real clinical settings,…
cs.AI2026
Clinical Harness for Governable Medical AI Skill Ecosystems
Tianhan Xu, Lei Bao, Zhe Hu +2
Medical AI remains organized around isolated models, whereas care requires accountable capabilities that persist across time. We define clinical AI skills and propose the Clinical…