重點導讀
醫療 AI 模型需要看懂影像、整理報告,也要能回答醫療問題。
- Ant Ling 發布開源多模態模型 LingSante-3.1-air-VL,結合醫療影像理解、報告生成、醫療推理、多模態搜尋與工具使用。
- 模型總引數為 124B,啟用引數為 5.5B。團隊表示,它在 AFUMED-Derm、AFUMED-Report、MIMIC-CXR 和醫療視覺問答的平均成績上,勝過比較的模型 GPT-6.1 Sol 和 Gemini 3.8 Flash。
- 在一般用途評測中,也有部分專案高於這兩個模型。
AI 伴隨問答
針對這篇報導有疑問?可直接點選快捷問題或向 AI 追問背景脈絡與技術細節:
Ant Ling@AntLingAGI
·58 分鐘前
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.
推文來源 · X (Twitter)在 X 參與討論