MIMO: A medical vision language model with visual referring multimodal input and pixel grounding multimodal output

• URL: http://arxiv.org/abs/2510.10011v1
• Date: Sat, 11 Oct 2025 04:29:09 GMT
• Title: MIMO: A medical vision language model with visual referring multimodal input and pixel grounding multimodal output
• Authors: Yanyuan Chen, Dexuan Xu, Yu Huang, Songkun Zhan, Hanpin Wang, Dongxue Chen, Xueping Wang, Meikang Qiu, Hang Li,
• Abstract summary: existing models are confronted with two issues: for input, the model only relies on text instructions and lacks direct understanding of visual clues in the image.<n>We propose a unified medical vision language model, with visual referring Multimodal Input and pixel grounding Multimodal Output.
• Score: 23.480960457981215
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Currently, medical vision language models are widely used in medical vision question answering tasks. However, existing models are confronted with two issues: for input, the model only relies on text instructions and lacks direct understanding of visual clues in the image; for output, the model only gives text answers and lacks connection with key areas in the image. To address these issues, we propose a unified medical vision language model MIMO, with visual referring Multimodal Input and pixel grounding Multimodal Output. MIMO can not only combine visual clues and textual instructions to understand complex medical images and semantics, but can also ground medical terminologies in textual output within the image. To overcome the scarcity of relevant data in the medical field, we propose MIMOSeg, a comprehensive medical multimodal dataset including 895K samples. MIMOSeg is constructed from four different perspectives, covering basic instruction following and complex question answering with multimodal input and multimodal output. We conduct experiments on several downstream medical multimodal tasks. Extensive experimental results verify that MIMO can uniquely combine visual referring and pixel grounding capabilities, which are not available in previous models.

Related papers

• UniMedVL: Unifying Medical Multimodal Understanding And Generation Through Observation-Knowledge-Analysis [41.864457631668806]
  We introduce UniMedVL, the first medical unified multimodal model for the simultaneous analysis of image understanding and generation tasks.<n>UniMedVL achieves superior performance on five medical image understanding benchmarks, while matching specialized models in generation quality across eight medical imaging modalities.
  arXiv  Detail & Related papers  (2025-10-17T14:54:58Z)
• Lingshu: A Generalist Foundation Model for Unified Multimodal Medical Understanding and Reasoning [57.873833577058]
  We build a multimodal dataset enriched with extensive medical knowledge.<n>We then introduce our medical-specialized MLLM: Lingshu.<n>Lingshu undergoes multi-stage training to embed medical expertise and enhance its task-solving capabilities.
  arXiv  Detail & Related papers  (2025-06-08T08:47:30Z)
• Towards a Multimodal Large Language Model with Pixel-Level Insight for Biomedicine [23.716953682681975]
  We introduce a novel end-to-end multimodal large language model for the biomedical domain, named MedPLIB.<n>It supports visual question answering (VQA), arbitrary pixel-level prompts (points, bounding boxes, and free-form shapes), and pixel-level grounding.<n>Results indicate that MedPLIB has achieved state-of-the-art outcomes across multiple medical visual language tasks.
  arXiv  Detail & Related papers  (2024-12-12T13:41:35Z)
• Parameter-Efficient Fine-Tuning Medical Multimodal Large Language Models for Medical Visual Grounding [9.144030136201476]
  Multimodal large language models (MLLMs) inherit the superior text understanding capabilities of LLMs and extend these capabilities to multimodal scenarios. These models achieve excellent results in the general domain of multimodal tasks. However, in the medical domain, the substantial training costs and the requirement for extensive medical data pose challenges to the development of medical MLLMs.
  arXiv  Detail & Related papers  (2024-10-31T11:07:26Z)
• Medical Vision-Language Pre-Training for Brain Abnormalities [96.1408455065347]
  We show how to automatically collect medical image-text aligned data for pretraining from public resources such as PubMed. In particular, we present a pipeline that streamlines the pre-training process by initially collecting a large brain image-text dataset. We also investigate the unique challenge of mapping subfigures to subcaptions in the medical domain.
  arXiv  Detail & Related papers  (2024-04-27T05:03:42Z)
• Language Is Not All You Need: Aligning Perception with Language Models [110.51362453720458]
  We introduce Kosmos-1, a Multimodal Large Language Model (MLLM) that can perceive general modalities, learn in context, and follow instructions. We train Kosmos-1 from scratch on web-scale multimodal corpora, including arbitrarily interleaved text and images, image-caption pairs, and text data. Experimental results show that Kosmos-1 achieves impressive performance on (i) language understanding, generation, and even OCR-free NLP. We also show that MLLMs can benefit from cross-modal transfer, i.e., transfer knowledge from language to multimodal, and from multimodal to language
  arXiv  Detail & Related papers  (2023-02-27T18:55:27Z)
• Towards Unifying Medical Vision-and-Language Pre-training via Soft Prompts [63.84720380390935]
  There exist two typical types, textiti.e., the fusion-encoder type and the dual-encoder type, depending on whether a heavy fusion module is used. We propose an effective yet straightforward scheme named PTUnifier to unify the two types. We first unify the input format by introducing visual and textual prompts, which serve as a feature bank that stores the most representative images/texts.
  arXiv  Detail & Related papers  (2023-02-17T15:43:42Z)
• Multi-Modal Masked Autoencoders for Medical Vision-and-Language Pre-Training [62.215025958347105]
  We propose a self-supervised learning paradigm with multi-modal masked autoencoders. We learn cross-modal domain knowledge by reconstructing missing pixels and tokens from randomly masked images and texts.
  arXiv  Detail & Related papers  (2022-09-15T07:26:43Z)
• MuVAM: A Multi-View Attention-based Model for Medical Visual Question Answering [2.413694065650786]
  This paper proposes a multi-view attention-based model(MuVAM) for medical visual question answering. It integrates the high-level semantics of medical images on the basis of text description. Experiments on two datasets show that the effectiveness of MuVAM surpasses the state-of-the-art method.
  arXiv  Detail & Related papers  (2021-07-07T13:40:25Z)
• Multi-modal Understanding and Generation for Medical Images and Text via Vision-Language Pre-Training [5.119201893752376]
  We propose Medical Vision Language Learner (MedViLL) which adopts a Transformer-based architecture combined with a novel multimodal attention masking scheme. We empirically demonstrate the superior downstream task performance of MedViLL against various baselines including task-specific architectures.
  arXiv  Detail & Related papers  (2021-05-24T15:14:09Z)
• Unsupervised Multimodal Neural Machine Translation with Pseudo Visual Pivoting [105.5303416210736]
  Unsupervised machine translation (MT) has recently achieved impressive results with monolingual corpora only. It is still challenging to associate source-target sentences in the latent space. As people speak different languages biologically share similar visual systems, the potential of achieving better alignment through visual content is promising.
  arXiv  Detail & Related papers  (2020-05-06T20:11:46Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.