MedXIAOHE: A Comprehensive Recipe for Building Medical MLLMs

TL;DR

MedXIAOHE is a comprehensive medical vision-language model that achieves state-of-the-art performance and incorporates advanced reasoning, knowledge coverage, and reliability features for clinical applications.

Contribution

It introduces an entity-aware continual pretraining framework and reinforcement learning-based reasoning methods for improved medical understanding and decision-making.

Findings

Achieves state-of-the-art results on diverse medical benchmarks.

Surpasses leading closed-source multimodal systems in multiple capabilities.

Enhances reasoning and reliability in medical AI applications.

Abstract

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.