NVIDIA open-sources NV-Reason-CT, a native 3D vision-language model for CT scans
NVIDIA Developer · youtube · 2026-10-09
NVIDIA released NV-Reason-CT, an open vision-language model that natively reads chest and abdominal CT volumes in 3D and reasons step by step to produce findings. A Primus 3D ViT encoder feeds Qwen3.5-4B end to end, passing all 13,824 visual tokens per 192×192×192 crop with 3D position tags — unlike 2D-oriented VLMs that sample slices or compress volumes. Model, demo, fine-tuning scripts (SFT/GRPO), and paper are public.
More from Models
- Emad Mostaque: OpenAI Burned $10-20M Compute Solving Navier-Stokes, Prices Falling Fast — rohanpaul_ai · 2026-10-09
- Musk touts Grok Bot upgrades: Opus 5.5 on demand, full X access, big speed gains — elonmusk · 2026-10-09
- Dev complains Opus 5.5 sneaks in 'tons of little fixes' without asking — rickasaurus · 2026-10-09
- FrontierCode Is a Private Cognition-Run Eval, Mistral Exec Clarifies — b_roziere · 2026-10-09
- Google ships a decision-making AI model into Chrome, tested against Gemini Nano and Decisions API — gaganghotra_ · 2026-10-09
- User feeds Grok Bot 60 seconds of screen recording, gets a surprisingly decent tutorial video — elonmusk · 2026-10-09