# RoiMAM: Region-of-Interest Medical Attention Model for Efficient Vision-Language Understanding

arXiv: https://arxiv.org/abs/2605.15561 · HTML: https://mlsanity.com/paper/2605.15561/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Medical vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 9 of its 16 references that are in the map.
- First posted on arXiv 15 May 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Medical vision-language models](https://mlsanity.com/mllm/medical-vision-language-models/)

## Builds on (most cited first, 9 of 9)

- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day](https://mlsanity.com/paper/2306.00890/) (2023)
- [SLAKE: A Semantically-Labeled Knowledge-Enhanced Dataset for Medical Visual Question Answering](https://mlsanity.com/paper/2102.09542/) (2021)
- [PMC-VQA: Visual Instruction Tuning for Medical Visual Question Answering](https://mlsanity.com/paper/2305.10415/) (2023)
- [PMC-CLIP: Contrastive Language-Image Pre-training using Biomedical Documents](https://mlsanity.com/paper/2303.07240/) (2023)
- [HuatuoGPT-Vision, Towards Injecting Medical Visual Knowledge into Multimodal LLMs at Scale](https://mlsanity.com/paper/2406.19280/) (2024)
- [SAM-Med2D](https://mlsanity.com/paper/2308.16184/) (2023)
- [UniMed-CLIP: Towards a Unified Image-Text Pretraining Paradigm for Diverse Medical Imaging Modalities](https://mlsanity.com/paper/2412.10372/) (2024)
- [Visual Explanations of Image-Text Representations via Multi-Modal Information Bottleneck Attribution](https://mlsanity.com/paper/2312.17174/) (2023)

## Abstract (arXiv)

Vision-Language Models (VLMs) facilitate medical visual question answering (MedVQA) by jointly interpreting images and text. However, existing models typically depend on large architectures and closed-set answers, which limits their efficiency and potential clinical applicability. To overcome these shortcomings, we introduce RoiMAM, an efficient VLM. It integrates a training-free ROI Generation Module with Semantic Selective Suppression to focus on lesion-relevant regions, alongside a Text Prompt Enhancer module that provides modality-specific context without introducing training parameters. Compared to the widely used MedVInT-TD model, our design achieves efficient and accurate diagnosis at less than 20% of the model size, while improving accuracy by approximately 2% on SLAKE and 4.6% on PMC-VQA.