跳到正文
Rohan Paul· @rohanpaul_ai · X·· 1 小时前AI 评分64
AI 导读

蚂蚁集团开源 LingSante-3.1-air-VL,这是一个能撰写胸部 X 光报告的医疗多模态模型。该模型为 MoE 架构,总参数 124B、每 token 激活 5.5B,作者称其在 3 项标准报告基准上均超过 GPT-6.1 Sol、Claude Opus 5.5 和 Gemini 3.8 Flash。其强化学习按临床意义、异常位置、误报和漏检对报告打分,奖励正确诊断而非模仿示例报告风格。

正文 · 原文

Ant Group just open-sourced LingSante-3.1-air-VL, a medical model that writes chest X-ray reports.

beats GPT-6.1 Sol, Claude Opus 5.5 and Gemini 3.8 Flash on all 3 standard report benchmarks.

its a mixture-of-experts (MoE) model with 124B total parameters, of which only 5.5B are active per token

its reinforcement learning scored each X-ray report on clinical meaning, abnormality location, false positives and missed findings, which rewards a correct diagnosis rather than only copying the style of example reports.

引用Ant Ling@AntLingAGI
Meet LingSante-3.1-air-VL, an open-source multimodal medical model with 124B total and 5.5B active parameters. It combines medical image understanding, report generation and medical reasoning with multimodal search and tool use. In our evaluation, it leads the compared models on AFUMED-Derm, AFUMED-Report, MIMIC-CXR and medical VQA (averaged across benchmarks), ahead of GPT-6.1 Sol, Gemini 3.8 Flash on all four. It also demonstrates strong general-purpose capabilities, scoring higher than GPT-6.1 Sol on BrowseComp-VL and Gemini 3.8 Flash on AndroidWorld, alongside competitive performance on MMSearch. Explore LingSante-3.1-air-VL and build with it.
在 X 查看被引用的帖子

来源:Rohan Paul · x.com