---
title: MedGRPO Demo — Medical Video Understanding
emoji: 🏥
colorFrom: blue
colorTo: indigo
sdk: gradio
sdk_version: "5.50.0"
app_file: app.py
pinned: false
license: apache-2.0
hardware: zero-a10g
---

# MedGRPO — Medical Video Understanding

Interactive demo for **uAI-NEXUS-MedVLM-1.0c-4B-SFT** (base: Qwen3.5-VL-4B) — part of the uAI-NEXUS-MedVLM 1.0 family, fine-tuned on [MedVidBench](https://huggingface.co/datasets/UII-AI/MedVidBench) for medical video question answering. The publicly released family member is [uAI-NEXUS-MedVLM-1.0a-7B-RL](https://huggingface.co/UII-AI/uAI-NEXUS-MedVLM-1.0a-7B-RL).

## Tasks

| Task | Description |
|------|-------------|
| **Temporal Action Localization** | Identify when surgical actions occur (start–end times) |
| **Spatiotemporal Grounding** | Locate instruments/anatomy in space and time |
| **Dense Captioning** | Time-stamped descriptions of action segments |
| **Next Action Prediction** | Predict the next procedural step |
| **Video Summary** | Summarize the surgical procedure |
| **Region Caption** | Describe activity of a specific instrument/region |
| **CVS Assessment** | Score Critical View of Safety criteria |
| **Skill Assessment** | Rate surgical skill (1–5 scale) |

## Data Sources

Examples drawn from 8 medical video datasets: AVOS, Cholec80-CVS, CholecT50, CholecTrack20, CoPESD, EgoSurgery, NurViD, and JIGSAWS.

## Links

- [Paper](https://arxiv.org/abs/2512.06581)
- [Project Page](https://uii-ai.github.io/MedGRPO/)
- [Model (uAI-NEXUS-MedVLM-1.0a-7B-RL)](https://huggingface.co/UII-AI/uAI-NEXUS-MedVLM-1.0a-7B-RL)
- [Inference Code](https://github.com/UII-AI/MedGRPO-Code)
- [MedVidBench](https://huggingface.co/datasets/UII-AI/MedVidBench)
- [MedVidBench Leaderboard](https://huggingface.co/spaces/UII-AI/MedVidBench-Leaderboard)