CS1: 4B Medical Decision Model Trained on 3.6M Patients Beats Open Rivals
AI4Pathology · x · 2026-10-22
AI4Pathology announces Clinical System One (CS1), a small, fast general-purpose decision model for medicine, in preprint. Health systems hold decades of notes and reports, but reading all of them for every question has always been too slow and expensive — even with LLMs. Trained on 12.4 million questions across 3.6 million patients, CS1-4B beats open decision models at reading real-world patient records.
More from Research
- HarnessAdapt-RL trains the coding agent's harness too, beating GRPO by 9.8 points on SWE-bench Verified — tencent · 2026-10-22
- BiDex-100: a 100+ task simulation benchmark for bimanual dexterous manipulation from Zhejiang U & Ant Group — Robbyant-Research · 2026-10-22
- ConfigWM: task-conditioned perception keeps world models robust to distractors, +22.3% over strongest baseline — Yijun Shen · 2026-10-22
- RLAWM defines 'modeling drift' and penalizes divergence from physical axioms to fix LLM physics reasoning — Xinye Yang · 2026-10-22
- SuperMimic cuts humanoid full-body control training GPU-hours by over 1000x — kevin_zakka · 2026-10-22
- Will math papers admit "the author cannot verify these details" in acknowledgements? — pickover · 2026-10-22