Quanta AI Labs

Alibaba DAMO Academy · Visual Understanding

ClinFusion

Medical multimodal model reading both 2D imaging (X-ray, ultrasound, CT) and 3D NIfTI volumes to answer clinical questions and draft reports. Built on Qwen3-VL with DINOv2 and ConvNeXt vision encoders, shipping at 8B and 32B. Reported to beat medical MLLMs on 20 of 24 benchmarks and GPT-4.5 and Gemini-3-Flash on 13 of 16, with board-certified radiologist review. Apache-2.0.

Open the source ↗

Similar Vision & Image releases

  • WeVisOne-VL

    WeChat Vision, Tencent · Vision-Language Model · Week 44, 2026

  • Nemotron 3.5 Super VL

    NVIDIA · Open Multimodal MoE · Week 43, 2026

  • Vision Demos

    jeremyipark · Sports Vision Demos · Week 41, 2026

  • PixelUMM

    NVIDIA and University of Waterloo · Encoder-Free Unified Model · Week 41, 2026

  • Ovis-Embedding

    ATH-MaaS · Ovis Embedding Models · Week 40, 2026

  • RADAR

    RADAR-Generalist team, published in Science · Abdominal CT Vision Model · Week 40, 2026

More from Alibaba DAMO Academy

  • RynnEC

    Alibaba DAMO Academy · Research Paper · Week 29, 2025

  • Babel

    Alibaba DAMO Academy · Multilingual · Week 7, 2025

Published by Quanta AI Labs, an AI agency in India. Browse every week in AI News Weekly.