mlsanityData to 14 Oct 2026

LLaDA-MedV: Exploring Large Language Diffusion Models for Biomedical Image Understanding

arXiv 2508.01617 ↗First posted 3 Aug 2025cs.CVcited by 13

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

also in 1 more
Abstract (arXiv)

Autoregressive models (ARMs) have long dominated the landscape of biomedical vision-language models (VLMs). Recently, masked diffusion models such as LLaDA have emerged as promising alternatives, yet their application in the biomedical domain remains largely underexplored. To bridge this gap, we introduce LLaDA-MedV, the first large language diffusion model tailored for biomedical image understanding through vision instruction tuning. LLaDA-MedV achieves relative performance gains of 7.855% over LLaVA-Med and 1.867% over LLaDA-V in the open-ended biomedical visual conversation task, and sets new state-of-the-art accuracy on the closed-form subset of three VQA benchmarks: 84.93% on VQA-RAD, 92.31% on SLAKE, and 95.15% on PathVQA. Furthermore, a detailed comparison with LLaVA-Med suggests that LLaDA-MedV is capable of generating reasonably longer responses by explicitly controlling response length, which can lead to more informative outputs. We also conduct an in-depth analysis of both the training and inference stages, highlighting the critical roles of initialization weight selection, fine-tuning strategies, and the interplay between sampling steps and response repetition. The code and model weight is released at https://github.com/LLM-VLM-GSL/LLaDA-MedV.

Key facts. Cited by 13 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 51 of its 60 references that are in the map. First posted on arXiv 3 Aug 2025.

Builds on

51 of 60 references.

Closest ancestors · 9

Same direction, newest first

  1. 2025Toward Effective Reinforcement Learning Fine-Tuning for Medical VQA in Vision-Language Models20 May
  2. 2025Med-R1: Reinforcement Learning for Generalizable Medical Reasoning in Vision-Language Models18 Mar
  3. 2025RetinalGPT: A Retinal Clinical Preference Conversational Assistant Powered by Large Vision-Language Models6 Mar
  4. 2025MedVLM-R1: Incentivizing Medical Reasoning Capability of Vision-Language Models (VLMs) via Reinforcement Learning26 Feb
  5. 2024How Does Diverse Interpretability of Textual Prompts Impact Medical Vision-Language Zero-Shot Tasks?31 Aug
  6. 2024Visual Prompt Engineering for Vision Language Models in Radiology28 Aug
  7. 2024Prompting Medical Large Vision-Language Models to Diagnose Pathologies by Visual Question Answering31 Jul
  8. 2023LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day1 Jun
  9. 2022Self-supervised vision-language pretraining for Medical visual question answering24 Nov

Other references · 42

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2023GPT-4 Technical Reportcited by 18,396
  4. 2022Training language models to follow instructions with human feedbackcited by 15,971
  5. 2024The Llama 3 Herd of Modelscited by 14,715
  6. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  7. 2020Denoising Diffusion Implicit Modelscited by 9,781
  8. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  9. 2023Visual Instruction Tuningcited by 7,869
  10. 2023Improved Baselines with Visual Instruction Tuningcited by 4,418
  11. 2023G-Eval: NLG Evaluation using GPT-4 with Better Human Alignmentcited by 2,276
  12. 2023Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyondcited by 2,224
30 more
  1. 2021Structured Denoising Diffusion Models in Discrete State-Spacescited by 1,719
  2. 2025SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Featurescited by 1,188
  3. 2022MaskGIT: Masked Generative Image Transformercited by 1,099
  4. 2022Diffusion-LM Improves Controllable Text Generationcited by 1,027
  5. 2025Large Language Diffusion Modelscited by 912
  6. 2024Simple and Effective Masked Diffusion Language Modelscited by 848
  7. 2023Discrete Diffusion Modeling by Estimating the Ratios of the Data Distributioncited by 745
  8. 2024Simplified and Generalized Masked Diffusion for Discrete Datacited by 626
  9. 2022MedCLIP: Contrastive Learning from Unpaired Medical Images and Textcited by 570
  10. 2020PathVQA: 30000+ Questions for Medical Visual Question Answeringcited by 475
  11. 2022DiffuSeq: Sequence to Sequence Text Generation with Diffusion Modelscited by 450
  12. 2021SLAKE: A Semantically-Labeled Knowledge-Enhanced Dataset for Medical Visual Question Answeringcited by 449
  13. 2023Med-Flamingo: a Multimodal Medical Few-shot Learnercited by 392
  14. 2024Your Absorbing Discrete Diffusion Secretly Models the Conditional Distributions of Clean Datacited by 381
  15. 2022Analog Bits: Generating Discrete Data using Diffusion Models with Self-Conditioningcited by 373
  16. 2024Scaling Diffusion Language Models via Adaptation from Autoregressive Modelscited by 274
  17. 2021ZeRO-Infinity: Breaking the GPU Memory Wall for Extreme Scale Deep Learningcited by 256
  18. 2023PMC-CLIP: Contrastive Language-Image Pre-training using Biomedical Documentscited by 212
  19. 2023Learning to Exploit Temporal Structure for Biomedical Vision-Language Processingcited by 211
  20. 2025Remasking Discrete Diffusion Models with Inference-Time Scalingcited by 189
  21. 2025LLaDA-V: Large Language Diffusion Models with Visual Instruction Tuningcited by 148
  22. 2022Self-conditioned Embedding Diffusion for Text Generationcited by 117
  23. 2023BioMedGPT: Open Multimodal Generative Pre-trained Transformer for BioMedicinecited by 100
  24. 2023TESS: Text-to-Text Self-Conditioned Simplex Diffusioncited by 65
  25. 2023Open-Ended Medical Visual Question Answering Through Prefix Tuning of Language Modelscited by 58
  26. 2023DINOISER: Diffused Conditional Sequence Learning by Manipulating Noisescited by 50
  27. 2022Categorical SDEs with Simplex Diffusioncited by 42
  28. 2023Q2ATransformer: Improving Medical VQA via an Answer Querying Decodercited by 31
  29. 2023GPT-4 as an Effective Zero-Shot Evaluator for Scientific Figure Captionscited by 21
  30. 2024GPT-4 as Evaluator: Evaluating Large Language Models on Pest Management in Agriculturecited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 5; 2026: 8.

13 papers.

Sort:

By area:

  1. 2025LLaDA-VLA: Vision Language Diffusion Action Modelscited by 30
  2. 2025Dream-VL & Dream-VLA: Open Vision-Language and Vision-Language-Action Models with Diffusion Language Model Backbonecited by 18
  3. 2025Test-Time Scaling in Diffusion LLMs via Hidden Semi-Autoregressive Expertscited by 8
  4. 2025Decoding Large Language Diffusion Models with Foreseeing Movementcited by 6
  5. 2026EZBlender: Efficient 3D Editing with Plan-and-ReAct Agentcited by 4
  6. 2026ECHO: Efficient Chest X-ray Report Generation with One-step Block Diffusioncited by 4
  7. 2025A DeepSeek-Powered AI System for Automated Chest Radiograph Interpretation in Clinical Practicecited by 2
  8. 2026OphIn-500K: Curating Web-Scale Visual Instructions for Scaling Ophthalmic Multimodal Large Language Modelscited by 1
  9. 2026MedFG-VQA: Low-Frequency Memory and Graph Attention for Lightweight Medical VQAcited by 1
  10. 2026Mags-RL: Wearing Multimodal LLMs a Magnifying Glass via Agentic Reinforcement Learning For Complex Scene Reasoningcited by 0
  11. 2026Diffusion-Proof: Recipe for Formal Theorem Proving Beyond Auto-Regressive Generationcited by 0
  12. 2026DRRG: A Discrete Diffusion Framework for Radiology Report Generationcited by 0
1 more
  1. 2026Intent-Triggered Anchoring for Multi-Token Format Units in Parallel Decoding of Diffusion Language Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Advancing High Resolution Vision-Language Models in Biomedicine
  2. 2025Scaling Up Biomedical Vision-Language Models: Fine-Tuning, Instruction Tuning, and Multi-Modal Learning
  3. 2026MMBU: A Massive Multi-modal Biomedical Understanding Benchmark to Probe the Perception Capabilities of Vision-Language Models
  4. 2026LLaDA2.0-Uni: Unifying Multimodal Understanding and Generation with Diffusion Large Language Model
  5. 2024A Refer-and-Ground Multimodal Large Language Model for Biomedicine
  6. 2025Taming Vision-Language Models for Medical Image Analysis: A Comprehensive Review
  7. 2026Instruction-Free Tuning of Large Vision Language Models for Medical Instruction Following
  8. 2024PA-LLaVA: A Large Language-Vision Assistant for Human Pathology Image Understanding