uAI NEXUS MedVLM 1.0a 7B RL Accepted at CVPR 2026 🎉 Base Model : Qwen2.5 VL 7B Instruct uAI NEXUS MedVLM 1.0a 7B RL is a medical video understanding model fine tuned from Qwen2.5 VL 7B Instruct. It is the 7B RL member of the uAI NEXUS MedVLM 1.0 family (variant a = Qwen2.5 VL base; variants b / c use Qwen3 VL 4B and Qwen3.5 4B respectively). Training uses a two stage pipeline: 1. Supervised Fine Tuning (SFT) on medical video QA data. 2. Group Relative Policy Optimization (GRPO) with task specific rewards for temporal precision and clinical semantics. It achieves state of the art performance on medical video understanding across temporal action localization, spatiotemporal grounding, video summarization, region captioning, and surgical skill/CVS assessment. 📄 Paper : arXiv:2512.06581 🌐 Project Page : uii ai.github.io/MedGRPO 💻 Code : github.com/UII AI/MedGRPO Code 🤗 Dataset : UII AI/MedVidBench 📊 Leaderboard : UII AI/MedVidBench Leaderboard Model Details Architecture : Qwen2.5 VL (7B parameters) — video + text Base Model : Qwen/Qwen2.5 VL 7B Instruct Training : SFT → GRPO Domain : Medical and surgical video understanding License : Apache 2.0 Supported Tasks The model handles 8…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy