# A Refer-and-Ground Multimodal Large Language Model for Biomedicine

arXiv: https://arxiv.org/abs/2406.18146 · HTML: https://mlsanity.com/paper/2406.18146/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Placed in Medical vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 19 of its 29 references that are in the map.
- First posted on arXiv 26 Jun 2024.

## Placed in

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

## Builds on (most cited first, 19 of 19)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond](https://mlsanity.com/paper/2308.12966/) (2023)
- [LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day](https://mlsanity.com/paper/2306.00890/) (2023)
- [SPICE: Semantic Propositional Image Caption Evaluation](https://mlsanity.com/paper/1607.08822/) (2016)
- [MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning](https://mlsanity.com/paper/2310.09478/) (2023)
- [NExT-GPT: Any-to-Any Multimodal LLM](https://mlsanity.com/paper/2309.05519/) (2023)
- [MedCLIP: Contrastive Learning from Unpaired Medical Images and Text](https://mlsanity.com/paper/2210.10163/) (2022)
- [Ferret: Refer and Ground Anything Anywhere at Any Granularity](https://mlsanity.com/paper/2310.07704/) (2023)
- [GPT4RoI: Instruction Tuning Large Language Model on Region-of-Interest](https://mlsanity.com/paper/2307.03601/) (2023)
- [Towards Generalist Biomedical AI](https://mlsanity.com/paper/2307.14334/) (2023)
- [AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling](https://mlsanity.com/paper/2402.12226/) (2024)
- [Towards Generalist Foundation Model for Radiology by Leveraging Web-scale 2D&3D Medical Data](https://mlsanity.com/paper/2308.02463/) (2023)
- [LViT: Language meets Vision Transformer in Medical Image Segmentation](https://mlsanity.com/paper/2206.14718/) (2022)
- [BioMedGPT: Open Multimodal Generative Pre-trained Transformer for BioMedicine](https://mlsanity.com/paper/2308.09442/) (2023)
- [SA-Med2D-20M Dataset: Segment Anything in 2D Medical Imaging with 20 Million masks](https://mlsanity.com/paper/2311.11969/) (2023)
- [Cross-Modal Conditioned Reconstruction for Language-guided Medical Image Segmentation](https://mlsanity.com/paper/2404.02845/) (2024)
- [SegICL: A Multimodal In-context Learning Framework for Enhanced Segmentation in Medical Imaging](https://mlsanity.com/paper/2403.16578/) (2024)

## Built on by (most cited first, 14 of 14)

- [Large Language Model with Region-guided Referring and Grounding for CT Report Generation](https://mlsanity.com/paper/2411.15539/) (2024)
- [Interpretable Bilingual Multimodal Large Language Model for Diverse Biomedical Tasks](https://mlsanity.com/paper/2410.18387/) (2024)
- [MedGround-R1: Advancing Medical Image Grounding via Spatial-Semantic Rewarded Group Relative Policy Optimization](https://mlsanity.com/paper/2507.02994/) (2025)
- [AOR: Anatomical Ontology-Guided Reasoning for Medical Large Multimodal Model in Chest X-Ray Interpretation](https://mlsanity.com/paper/2505.02830/) (2025)
- [Region-Aware Multimodal Large Language Model via SlowFast Tokenization and Pseudo-Mask Guidance for 3D CT Report Generation](https://mlsanity.com/paper/2506.23102/) (2025)
- [MedGround: Bridging the Evidence Gap in Medical Vision-Language Models with Verified Grounding Data](https://mlsanity.com/paper/2601.06847/) (2026)
- [RAU: Reference-based Anatomical Understanding with Vision Language Models](https://mlsanity.com/paper/2509.22404/) (2025)
- [MedReason-R1: Learning to Reason for CT Diagnosis with Reinforcement Learning and Local Zoom](https://mlsanity.com/paper/2510.19626/) (2025)
- [ClinKD: Cross-Modal Clinical Knowledge Distiller For Multi-Task Medical Images](https://mlsanity.com/paper/2502.05928/) (2025)
- [PathVG: A New Benchmark and Dataset for Pathology Visual Grounding](https://mlsanity.com/paper/2502.20869/) (2025)
- [Multi-Modal Explainable Medical AI Assistant for Trustworthy Human-AI Collaboration](https://mlsanity.com/paper/2505.06898/) (2025)
- [Step-CoT: Stepwise Visual Chain-of-Thought for Medical Visual Question Answering](https://mlsanity.com/paper/2603.13878/) (2026)
- [Aloe-Vision: Robust Vision-Language Models for Healthcare](https://mlsanity.com/paper/2606.27500/) (2026)
- [EVLF-FM: Explainable Vision Language Foundation Model for Medicine](https://mlsanity.com/paper/2509.24231/) (2025)

## Abstract (arXiv)

With the rapid development of multimodal large language models (MLLMs), especially their capabilities in visual chat through refer and ground functionalities, their significance is increasingly recognized. However, the biomedical field currently exhibits a substantial gap in this area, primarily due to the absence of a dedicated refer and ground dataset for biomedical images. To address this challenge, we devised the Med-GRIT-270k dataset. It comprises 270k question-and-answer pairs and spans eight distinct medical imaging modalities. Most importantly, it is the first dedicated to the biomedical domain and integrating refer and ground conversations. The key idea is to sample large-scale biomedical image-mask pairs from medical segmentation datasets and generate instruction datasets from text using chatGPT. Additionally, we introduce a Refer-and-Ground Multimodal Large Language Model for Biomedicine (BiRD) by using this dataset and multi-task instruction learning. Extensive experiments have corroborated the efficacy of the Med-GRIT-270k dataset and the multi-modal, fine-grained interactive capabilities of the BiRD model. This holds significant reference value for the exploration and development of intelligent biomedical assistants.