FreedomIntelligence

发现一个浏览器里就能学习三维人体解剖的平台 可以很方便的认识人体结构，理解身体如何运作 包含约 2,900 个解剖结构、12 个人体系统和140项动态演示入口 如果你在学习医学或者想做人体探索，医学科普小游戏 那这个项目可以作为参考 FreedomIntelligence/BodyVista 上面是github仓库 下面是在线查看 freedomintelligence.github.io @RongshengWang 推荐的

在线体验：freedomintelligence.github.io GitHub：FreedomIntelligence/BodyVista

【MedClaw｜基于 NanoClaw 打造的开源医学 AI 助手】 ✅ 检索 PubMed +14 个生物医学数据库 ✅ 医学报告、病历通俗化解读 ✅ 生成专科文献研究简报 ✅ 辅助医学生备考 USMLE ✅ 接入 WhatsApp / Telegram / 飞书 每个群组拥有独立隔离工作空间，完全开源！ 项目地址： github.com/FreedomIntelligence/OpenClaw-Medical-S… #OpenSourceAI #MedicalAgent #OpenClaw

@_klimvs @M_Chmurka W badaniach wyszło że AI zbiera wywiad dużo lepiej niż człowiek. Oczywiście AI dedykowane do zbierania wywiadu, nie "chatgpt zbierz wywiad". Nawet prosty skill agenta mógł by zebrać niezły wywiad. Coś takiego to minimum żeby w ogóle rozmawiać o AI FreedomIntelligence/OpenClaw-Medical-Skills

HuatuoGPT-3: RL-Only Domain Adaptation from Base Models Domain adaptation aims to turn a general-purpose large language model (LLM) into an expert for a target domain. While the dominant SFT+RL pipeline offers a convenient cold start, it may reduce exploration diversity and introduces additional complexity through multi-stage optimization. These limitations motivate RL-only adaptation. However, pure on-policy RL suffers from a cold-start problem, while mixed-policy RL still falls short: informative tokens in teacher outputs are learned too slowly in early training, and stale teacher outputs can hinder later improvement. We identify these two failure modes as Gradient Starvation and Teacher-Distribution Anchoring. To address them, we propose One-stage Policy Optimization (OnePO), which treats teacher outputs as transient guidance for policy improvement. OnePO combines Adaptive Objective Evolution to strengthen learning on informative low-probability teacher tokens and Teacher Retirement to discard teacher outputs once the current policy can surpass them. On medical adaptation, OnePO achieves 67.2 on HealthBench (Total) with only 20K training samples, outperforming SFT+RL and pure RL by 2.7 and 7.4 points, respectively. We further scale OnePO to produce HuatuoGPT-3, an open-source medical LLM series whose 27B variant reaches 70.1 on HealthBench (Total) and 71.4 on HealthBench Professional, surpassing frontier models such as GPT-6 Astra. Models and code are available at FreedomIntelligence/HuatuoGPT-3. Comments: Extended version of "OnePO: Direct One-stage Policy Optimization for SFT-free Domain Adaptation", accepted at ICML 2026, with additional analysis and scaling to HuatuoGPT-3