# UniReason-Med: A Shared Grounded Reasoning Interface for 2D-to-3D Transfer in Medical VQA

arXiv: https://arxiv.org/abs/2606.11740 · HTML: https://mlsanity.com/paper/2606.11740/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 26 references that are in the map.
- First posted on arXiv 10 Jun 2026.

## Builds on (most cited first, 14 of 14)

- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day](https://mlsanity.com/paper/2306.00890/) (2023)
- [Kvasir-SEG: A Segmented Polyp Dataset](https://mlsanity.com/paper/1911.07069/) (2019)
- [DeepEyes: Incentivizing "Thinking with Images" via Reinforcement Learning](https://mlsanity.com/paper/2505.14362/) (2025)
- [Pixel Reasoner: Incentivizing Pixel-Space Reasoning with Curiosity-Driven Reinforcement Learning](https://mlsanity.com/paper/2505.15966/) (2025)
- [Lingshu: A Generalist Foundation Model for Unified Multimodal Medical Understanding and Reasoning](https://mlsanity.com/paper/2506.07044/) (2025)
- [OmniMedVQA: A New Large-Scale Comprehensive Evaluation Benchmark for Medical LVLM](https://mlsanity.com/paper/2402.09181/) (2024)
- [GRIT: Teaching MLLMs to Think with Images](https://mlsanity.com/paper/2505.15879/) (2025)
- [SA-Med2D-20M Dataset: Segment Anything in 2D Medical Imaging with 20 Million masks](https://mlsanity.com/paper/2311.11969/) (2023)
- [MINT-CoT: Enabling Interleaved Visual Tokens in Mathematical Chain-of-Thought Reasoning](https://mlsanity.com/paper/2506.05331/) (2025)
- [MedGround-R1: Advancing Medical Image Grounding via Spatial-Semantic Rewarded Group Relative Policy Optimization](https://mlsanity.com/paper/2507.02994/) (2025)
- [BiMediX2: Bio-Medical EXpert LMM for Diverse Medical Modalities](https://mlsanity.com/paper/2412.07769/) (2024)
- [OmniV-Med: Scaling Medical Vision-Language Model for Universal Visual Understanding](https://mlsanity.com/paper/2504.14692/) (2025)
- [V2T-CoT: From Vision to Text Chain-of-Thought for Medical Reasoning and Diagnosis](https://mlsanity.com/paper/2506.19610/) (2025)

## Built on by (most cited first, 2 of 2)

- [Towards Enhancing 3D Spatial Reasoning in Medical Multimodal Large Language Models](https://mlsanity.com/paper/2607.13860/) (2026)
- [Volumetric Radiology AI in the Era of Multimodal Large Language Models](https://mlsanity.com/paper/2608.20549/) (2026)

## Abstract (arXiv)

We study whether grounded reasoning supervision from abundant 2D medical images can improve 3D medical VQA when both input types are aligned through a common reasoning interface. We introduce UniReason-Med, a single-checkpoint framework that processes either a 2D image or a slice-serialized 3D volume at inference time, generating interleaved textual reasoning and localized visual evidence through shared box syntax, region-token injection, and a common grounded reasoning policy. To train this interface, we construct UniMed-CoT, a 220K instruction-tuning dataset with interleaved textual reasoning and grounded visual evidence, including 170K 2D and 50K 3D samples. Through supervised fine-tuning followed by outcome-level reinforcement learning, UniReason-Med learns to generate grounded reasoning traces without IoU/Dice-based localization rewards during RL. Data-mixture and component ablations show that joint 2D+3D grounded supervision substantially improves 3D reasoning over 3D-only training, while grounding and region-token injection consistently benefit both 2D and 3D tasks. These results suggest that a shared grounded reasoning interface can transfer reasoning structure from 2D images to slice-serialized volumetric medical understanding. The code and data are publicly available at https://github.com/IQuestLab/unireason-med.