NVIDIA open-sources NV-Reason-CT, a 3D CT reasoning VLM that halved reporting time in pilot
CeoImed · x · 2026-09-28
NVIDIA's medtech team open-sourced NV-Reason-CT, a generative vision-language model for native 3D chest/abdominal CT interpretation supporting abnormality classification, structured report generation, VQA, and interactive reasoning.
- Architecture: Qwen3.5-4B LM + 3D ViT (Primus, initialized with COLIPRI weights), ingesting NIfTI volumes directly
- Pilot: 2 physicians, 10 cases — reading and reporting time roughly halved
- Released: weights and code on Hugging Face; inference, SFT, and GRPO training examples on GitHub
- Research only, not a medical device
Related event: NVIDIA open-sources 3D CT reasoning model NV-Reason-CT(2 posts)→
More from Research
- Stanford lands $25M NIH grant to build AI center for personalized dementia care — StanfordAILab · 2026-09-29
- RL Gains May Hit a Wall: Verifiable Data Limits and Stalling nanochart Benchmarks — QuintinPope5 · 2026-09-29
- TALES Benchmark on LLM Game-Playing Accepted to NeurIPS 2026, New Results Coming — tw_killian · 2026-09-29
- UBC's Schmidt wins ECML PKDD Test of Time Award for 2016 gradient convergence paper cited 2,000+ times — MarkSchmidtUBC · 2026-09-29
- Amazon AGI's AutoGym auto-generates tasks, environments, and verifiers for agent RL training — omarsar0 · 2026-09-29
- RECLAIM preprint: best AI agent reproduces only 41% of papers with code, 15% without — VraserX · 2026-09-29