mlsanityData to 7 Oct 2026

MedGround: Bridging the Evidence Gap in Medical Vision-Language Models with Verified Grounding Data

arXiv 2601.06847 ↗First posted 11 Jan 2026cs.CV cs.AIcited by 5

On the map: Multimodal LLMs / vision-language models → Medical vision-language models

Abstract (arXiv)

Vision-Language Models (VLMs) can generate convincing clinical narratives, yet frequently struggle to visually ground their statements. We posit that this limitation arises from the scarcity of high-quality, large-scale clinical referring-localization pairs. To address this, we introduce MedGround, an automated pipeline that transforms segmentation resources into high-quality medical referring grounding data. Leveraging expert masks as spatial anchors, MedGround precisely derives localization targets, extracts shape and spatial cues, and guides VLMs to synthesize natural, clinically grounded queries that reflect morphology and location. To ensure data rigor, a multi-stage verification system integrates strict formatting checks, geometry- and medical-prior rules, and image-based visual judging to filter out ambiguous or visually unsupported samples. Finally, we present MedGround-35K, a novel multimodal medical dataset. Extensive experiments demonstrate that VLMs trained with MedGround-35K consistently achieve improved referring grounding performance, enhance multi-object semantic disambiguation, and exhibit strong generalization to unseen grounding settings. This work highlights MedGround as a scalable, data-driven approach to anchor medical language to verifiable visual evidence.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Placed in Medical vision-language models, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 43 of its 64 references that are in the map. First posted on arXiv 11 Jan 2026.

Builds on

43 of 64 references.

Closest ancestors · 14

Same direction, newest first

  1. 2025Enhancing Radiology Report Generation and Visual Grounding using Reinforcement Learning11 Dec
  2. 2025Evaluating Reasoning Faithfulness in Medical Vision-Language Models using Multimodal Perturbations13 Oct
  3. 2025MIMO: A medical vision language model with visual referring multimodal input and pixel grounding multimodal output11 Oct
  4. 2025MedCLM: Learning to Localize and Reason via a CoT-Curriculum in Medical Vision-Language Models6 Oct
  5. 2025Lingshu: A Generalist Foundation Model for Unified Multimodal Medical Understanding and Reasoning8 Jun
  6. 2025MedSG-Bench: A Benchmark for Medical Image Sequences Grounding17 May
  7. 2025MedVLM-R1: Incentivizing Medical Reasoning Capability of Vision-Language Models (VLMs) via Reinforcement Learning26 Feb
  8. 2024Towards a Multimodal Large Language Model with Pixel-Level Insight for Biomedicine12 Dec
  9. 2024VILA-M3: Enhancing Vision-Language Models with Medical Expert Knowledge19 Nov
  10. 2024A Refer-and-Ground Multimodal Large Language Model for Biomedicine26 Jun
  11. 2024M3D: Advancing 3D Medical Image Analysis with Multi-Modal Large Language Models31 Mar
  12. 2024Anatomical Structure-Guided Medical Vision-Language Pre-training14 Mar
2 more
  1. 2023Qilin-Med-VL: Towards Chinese Large Vision-Language Model for General Healthcare27 Oct
  2. 2023LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day1 Jun

Other references · 29

  1. 2025Qwen2.5-VL Technical Reportcited by 5,418
  2. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,274
  3. 2021Grounded Language-Image Pre-trainingcited by 1,147
  4. 2017ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseasescited by 969
  5. 2021MDETR -- Modulated Detection for End-to-End Multi-Modal Understandingcited by 811
  6. 2024MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategiescited by 694
  7. 2023RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignmentcited by 672
  8. 2017Skin Lesion Analysis Toward Melanoma Detection: A Challenge at the 2017 International Symposium on Biomedical Imaging (ISBI), Hosted by the International Skin Imaging Collaboration (ISIC)cited by 549
  9. 2025MedGemma Technical Reportcited by 398
  10. 2023Med-Flamingo: a Multimodal Medical Few-shot Learnercited by 387
  11. 2022Making the Most of Text Semantics to Improve Biomedical Vision--Language Processingcited by 336
  12. 2023PMC-VQA: Visual Instruction Tuning for Medical Visual Question Answeringcited by 333
17 more
  1. 2023Med-HALT: Medical Domain Hallucination Test for Large Language Modelscited by 156
  2. 2024MAIRA-2: Grounded Radiology Report Generationcited by 140
  3. 2024GREEN: Generative Radiology Report Evaluation and Error Notationcited by 124
  4. 2020MosMedData: Chest CT Scans With COVID-19 Related Findings Datasetcited by 103
  5. 2021Chest ImaGenome Dataset for Clinical Reasoningcited by 89
  6. 2023MedViT: A Robust Vision Transformer for Generalized Medical Image Classificationcited by 89
  7. 2024Advancing Multimodal Medical Capabilities of Geminicited by 88
  8. 2020COVID-19 Infection Map Generation and Detection from Chest X-Ray Imagescited by 28
  9. 2022Weakly-supervised segmentation of referring expressionscited by 21
  10. 2023RadGraph2: Modeling Disease Progression in Radiology Reports via Hierarchical Information Extractioncited by 11
  11. 2025New Dataset and Methods for Fine-Grained Compositional Referring Expression Comprehension via Specialist-MLLM Collaborationcited by 7
  12. 2025Med-GLIP: Advancing Medical Language-Image Pre-training with Large-scale Grounded Datasetcited by 7
  13. 2022BriFiSeg: a deep learning-based method for semantic and instance segmentation of nuclei in brightfield imagescited by 5
  14. 2025Anatomical grounding pre-training for medical phrase groundingcited by 5
  15. 2024Evaluating Automated Radiology Report Quality through Fine-Grained Phrasal Grounding of Clinical Findingscited by 3
  16. 2025ClinKD: Cross-Modal Clinical Knowledge Distiller For Multi-Task Medical Imagescited by 2
  17. 2025Generalised Medical Phrase Groundingcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 5.

5 papers.

  1. 2026Enhancing Medical Visual Grounding via Knowledge-guided Spatial Promptscited by 1
  2. 2026BioFact-MoE: Biologically Factorized Mixture of Experts for Vision-Language Prognostic Modeling in Hepatocellular Carcinomacited by 0
  3. 2026MedVol-R1: Reward-Driven Evidence Grounding for Volumetric Reasoning Segmentationcited by 0
  4. 2026LocAnyMed: Vision-Language Grounding for Multimodal Medical Imagescited by 0
  5. 2026Learning Where to Look: Anatomical Grounding and Guided Attention for Cardiac MRI Vision-Language Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026How Do Medical MLLMs Fail? A Study on Visual Grounding in Medical Images
  2. 2026From Reasoning to Pixels: Grounded Medical Multimodal LLMs for VQA and Segmentation
  3. 2026Why Does Grounding Hurt Medical VQA? Benchmarking, Diagnosis, and Fine-Tuning of Vision-Language Models
  4. 2024Parameter-Efficient Fine-Tuning Medical Multimodal Large Language Models for Medical Visual Grounding
  5. 2024Uncertainty-aware Medical Diagnostic Phrase Identification and Grounding
  6. 2025Knowledge to Sight: Reasoning over Visual Attributes via Knowledge Decomposition for Abnormality Grounding
  7. 2025MedReasoner: Reinforcement Learning Drives Reasoning Grounding from Clinical Thought to Pixel-Level Precision
  8. 2025Enhancing Abnormality Grounding for Vision Language Models with Knowledge Descriptions