Nolla Health trains Nemotron 3.5 VL for clinical diagnosis, nearly doubling accuracy to 66.8%
LoganGrasby · x · 2026-10-16
- Healthcare startup Nolla Health, working with TrainLoop AI, fine-tuned NVIDIA Nemotron 3.5 Super VL to interpret clinical images and conduct patient consultations, publishing results as an NVIDIA launch partner.
- Visual diagnosis accuracy jumped from 35.0% to 66.8%, beating tested frontier models on their internal evaluation.
- The approach involved building training environments that reflect varied health cases and how care unfolds over time; the author reports encouraging initial results with a detailed thread to follow.
Related event: Nolla Health Post-Trains Nemotron 3.5 VL for Clinical Diagnosis(3 posts)→
More from Models
- ChatGPT voice selection breaks after GPT-Live-1.1 rollout on Android — shaunralston · 2026-10-16
- vLLM officially supports Muse Spark Open: multimodal, 1M context, agentic — vllm_project · 2026-10-16
- Liquid AI ships LFM2.5-24B-A2B: 24B MoE with 2B active params for local agents — JosephJacks_ · 2026-10-16
- Cherry pi on a Raspberry Pi: the tiny-model rumor developers are watching — sull · 2026-10-16
- anon-1b: an open-weights Gemma fine-tune trained on 4chan greentext — rickasaurus · 2026-10-16
- Astra 6.1 reportedly delayed while OpenAI's frontier RL stays paused over safety concerns — haider1 · 2026-10-16