MedXIAOHE: A Comprehensive Recipe for Building Medical MLLMs
ByteDance XiaoHe Medical AI（字节跳动小荷医疗AI）
Baorong Shi, Bo Cui, Boyuan Jiang, Deli Yu, Fang Qian, Haihua Yang, Huichao Wang, Jiale Chen, Jianfei Pan, Jieqiong Cao, Jinghao Lin, Kai Wu, Lin Yang, Shengshe… 展开作者
Baorong Shi, Bo Cui, Boyuan Jiang, Deli Yu, Fang Qian, Haihua Yang, Huichao Wang, Jiale Chen, Jianfei Pan, Jieqiong Cao, Jinghao Lin, Kai Wu, Lin Yang, Shengsheng Yao, Tao Chen, Xiaojun Xiao, Xiaozhong Ji, Xu Wang, Yijun He, Zhixiong Yang
备注：
XIAOHE Medical AI team. See paper for full author list. Currently, the model is exclusively available on XIAOHE AI Doctor, accessible via both the App Store and the Douyin Mini Program. Updated to improve the layout
We present MedXIAOHE, a medical vision-language foundation model designed to advance general-purpose medical understanding and reasoning in real-world clinical applications. MedXIAOHE achieves state-of-the-art performance across diverse medical benchmarks and surpasses leading closed-source multimodal systems on multiple capabilities. To achieve this, we propose an entity-aware continual pretraining framework that organizes heterogeneous medical corpora to broaden knowledge coverage and reduce long-tail gaps (e.g., rare diseases). For medical expert-level reasoning and interaction, MedXIAOHE incorporates diverse medical reasoning patterns via reinforcement learning and tool-augmented agentic training, enabling multi-step diagnostic reasoning with verifiable decision traces. To improve reliability in real-world use, MedXIAOHE integrates user-preference rubrics, evidence-grounded reasoning, and low-hallucination long-form report generation, with improved adherence to medical instructions. We release this report to document our practical design choices, scaling insights, and evaluation framework, hoping to inspire further research.
InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models
Shanghai AI Laboratory（上海人工智能实验室）；SenseTime Research（商汤科技研究院）；Tsinghua University（清华大学）；Nanjing University（南京大学）；Fudan University（复旦大学）；The Chinese University of Hong Kong（香港中文大学）；Shanghai Jiao Tong University（上海交通大学）
NaViL: Rethinking Scaling Properties of Native Multimodal Large Language Models under Data Constraints
Shanghai AI Laboratory（上海人工智能实验室）；The Chinese University of Hong Kong（香港中文大学）；Tsinghua University（清华大学）；Sensetime Research（商汤科技研究院）；Nanjing University（南京大学）
Towards Scalable Lightweight GUI Agents via Multi-role Orchestration
Zhejiang Key Laboratory of Accessible Perception and Intelligent Systems, Zhejiang University（浙江可及感知与智能系统重点实验室，浙江大学）；College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院）；AntGroup（蚂蚁集团）
The Chinese University of Hong Kong Shanghai AI Laboratory（香港中文大学上海人工智能实验室）；Shanghai AI Laboratory（上海人工智能实验室）；Shanghai Jiao Tong University（上海交通大学）；Shanghai Innovation Institute（上海创新研究院）
