# MedVersa: A Generalist Foundation Model for Medical Image Interpretation

arXiv: https://arxiv.org/abs/2405.07988 · HTML: https://mlsanity.com/paper/2405.07988/

## Key facts

- Cited by 38 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 May 2024.

## Built on by (most cited first, 30 of 38)

- [MAIRA-2: Grounded Radiology Report Generation](https://mlsanity.com/paper/2406.04449/) (2024)
- [Visual Large Language Models for Generalized and Specialized Applications](https://mlsanity.com/paper/2501.02765/) (2025)
- [Libra: Leveraging Temporal Images for Biomedical Radiology Analysis](https://mlsanity.com/paper/2411.19378/) (2024)
- [ReXGradient-160K: A Large-Scale Publicly Available Dataset of Chest Radiographs with Free-text Reports](https://mlsanity.com/paper/2505.00228/) (2025)
- [Interpretable Bilingual Multimodal Large Language Model for Diverse Biomedical Tasks](https://mlsanity.com/paper/2410.18387/) (2024)
- [RadFlag: A Black-Box Hallucination Detection Method for Medical Vision Language Models](https://mlsanity.com/paper/2411.00299/) (2024)
- [Automated Structured Radiology Report Generation](https://mlsanity.com/paper/2505.24223/) (2025)
- [Activating Associative Disease-Aware Vision Token Memory for LLM-Based X-ray Report Generation](https://mlsanity.com/paper/2501.03458/) (2025)
- [RADAR: Enhancing Radiology Report Generation with Supplementary Knowledge Injection](https://mlsanity.com/paper/2505.14318/) (2025)
- [ReXErr: Synthesizing Clinically Meaningful Errors in Diagnostic Radiology Reports](https://mlsanity.com/paper/2409.10829/) (2024)
- [Scaling medical imaging report generation with multimodal reinforcement learning](https://mlsanity.com/paper/2601.17151/) (2026)
- [From Text to Multimodality: Exploring the Evolution and Impact of Large Language Models in Medical Practice](https://mlsanity.com/paper/2410.01812/) (2024)
- [DDaTR: Dynamic Difference-aware Temporal Residual Network for Longitudinal Radiology Report Generation](https://mlsanity.com/paper/2505.03401/) (2025)
- [Lunguage: A Benchmark for Structured and Sequential Chest X-ray Interpretation](https://mlsanity.com/paper/2505.21190/) (2025)
- [Uncovering Knowledge Gaps in Radiology Report Generation Models through Knowledge Graphs](https://mlsanity.com/paper/2408.14397/) (2024)
- [Can Medical Vision-Language Pre-training Succeed with Purely Synthetic Data?](https://mlsanity.com/paper/2410.13523/) (2024)
- [MAIRA-Seg: Enhancing Radiology Report Generation with Segmentation-Aware Multimodal Large Language Models](https://mlsanity.com/paper/2411.11362/) (2024)
- [A Survey of Deep Learning-based Radiology Report Generation Using Multimodal Data](https://mlsanity.com/paper/2405.12833/) (2024)
- [A unified multi-task framework enables interpretable chest radiograph analysis](https://mlsanity.com/paper/2606.03417/) (2026)
- [A Reasoning-Enabled Vision-Language Foundation Model for Chest X-ray Interpretation](https://mlsanity.com/paper/2604.00493/) (2026)
- [EditGRPO: Reinforcement Learning with Post-Rollout Edits for Clinically Accurate Chest X-Ray Report Generation](https://mlsanity.com/paper/2509.22812/) (2025)
- [Clinically Grounded Agent-based Report Evaluation: An Interpretable Metric for Radiology Report Generation](https://mlsanity.com/paper/2508.02808/) (2025)
- [A Review of Longitudinal Radiology Report Generation: Dataset Composition, Methods, and Performance Evaluation](https://mlsanity.com/paper/2510.12444/) (2025)
- [Enhancing Reinforcement Learning for Radiology Report Generation with Evidence-aware Rewards and Self-correcting Preference Learning](https://mlsanity.com/paper/2604.13598/) (2026)
- [MedCTA: A Benchmark for Clinical Tool Agents](https://mlsanity.com/paper/2606.11702/) (2026)
- [Online Iterative Self-Alignment for Radiology Report Generation](https://mlsanity.com/paper/2505.11983/) (2025)
- [Boosting Medical Visual Understanding From Multi-Granular Language Learning](https://mlsanity.com/paper/2511.15943/) (2025)
- [Foundation Models in Biomedical Imaging: Turning Hype into Reality](https://mlsanity.com/paper/2512.15808/) (2025)
- [A data- and compute-efficient chest X-ray foundation model beyond aggressive scaling](https://mlsanity.com/paper/2602.22843/) (2026)
- [Agentic retrieval-augmented reasoning reshapes collective reliability under model variability in radiology question answering](https://mlsanity.com/paper/2603.06271/) (2026)

## Abstract (arXiv)

Current medical AI systems are often limited to narrow applications, hindering widespread adoption. We present MedVersa, a generalist foundation model trained on tens of millions of compiled medical instances. MedVersa unlocks generalist learning from multimodal inputs and outputs, representing the first example of a generalist model reaching competitive performance with leading specialized solutions across a variety of medical imaging scenarios. MedVersa achieves state-of-the-art performance in nine tasks, sometimes outperforming counterparts by over 10%. Radiologist evaluation shows MedVersa-generated reports get superior performance in 95% of normal studies, while matching or exceeding human reports in 71% of cases overall. User studies showed notable reductions in report writing time and discrepancies with the use of MedVersa. Our findings underscore the value of flexible, multimodal AI systems in advancing medical image interpretation and supporting clinical expertise.