MedXIAOHE: A Comprehensive Recipe for Building Medical MLLMs

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Shi, Baorong, Cui, Bo, Jiang, Boyuan, Yu, Deli, Qian, Fang, Yang, Haihua, Wang, Huichao, Chen, Jiale, Pan, Jianfei, Cao, Jieqiong, Lin, Jinghao, Wu, Kai, Yang, Lin, Yao, Shengsheng, Chen, Tao, Xiao, Xiaojun, Ji, Xiaozhong, Wang, Xu, He, Yijun, Yang, Zhixiong
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908940469534720
author Shi, Baorong
Cui, Bo
Jiang, Boyuan
Yu, Deli
Qian, Fang
Yang, Haihua
Wang, Huichao
Chen, Jiale
Pan, Jianfei
Cao, Jieqiong
Lin, Jinghao
Wu, Kai
Yang, Lin
Yao, Shengsheng
Chen, Tao
Xiao, Xiaojun
Ji, Xiaozhong
Wang, Xu
He, Yijun
Yang, Zhixiong
author_facet Shi, Baorong
Cui, Bo
Jiang, Boyuan
Yu, Deli
Qian, Fang
Yang, Haihua
Wang, Huichao
Chen, Jiale
Pan, Jianfei
Cao, Jieqiong
Lin, Jinghao
Wu, Kai
Yang, Lin
Yao, Shengsheng
Chen, Tao
Xiao, Xiaojun
Ji, Xiaozhong
Wang, Xu
He, Yijun
Yang, Zhixiong
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2602_12705
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle MedXIAOHE: A Comprehensive Recipe for Building Medical MLLMs
Shi, Baorong
Cui, Bo
Jiang, Boyuan
Yu, Deli
Qian, Fang
Yang, Haihua
Wang, Huichao
Chen, Jiale
Pan, Jianfei
Cao, Jieqiong
Lin, Jinghao
Wu, Kai
Yang, Lin
Yao, Shengsheng
Chen, Tao
Xiao, Xiaojun
Ji, Xiaozhong
Wang, Xu
He, Yijun
Yang, Zhixiong
Computation and Language
Artificial Intelligence
Computer Vision and Pattern Recognition
Image and Video Processing
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.
title MedXIAOHE: A Comprehensive Recipe for Building Medical MLLMs
topic Computation and Language
Artificial Intelligence
Computer Vision and Pattern Recognition
Image and Video Processing
url https://arxiv.org/abs/2602.12705