mlsanityData to 14 Oct 2026

RL4Med-DDPO: Reinforcement Learning for Controlled Guidance Towards Diverse Medical Image Generation using Vision-Language Foundation Models

arXiv 2503.15784 ↗First posted 20 Mar 2025cs.CVcited by 5

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

also in 2 more
Abstract (arXiv)

Vision-Language Foundation Models (VLFM) have shown a tremendous increase in performance in terms of generating high-resolution, photorealistic natural images. While VLFMs show a rich understanding of semantic content across modalities, they often struggle with fine-grained alignment tasks that require precise correspondence between image regions and textual descriptions, a limitation in medical imaging, where accurate localization and detection of clinical features are essential for diagnosis and analysis. To address this issue, we propose a multi-stage architecture where a pre-trained VLFM (e.g. Stable Diffusion) provides a cursory semantic understanding, while a reinforcement learning (RL) algorithm refines the alignment through an iterative process that optimizes for understanding semantic context. The reward signal is designed to align the semantic information of the text with synthesized images. Experiments on the public ISIC2019 skin lesion dataset demonstrate that the proposed method improves (a) the quality of the generated images, and (b) the alignment with the text prompt over the original fine-tuned Stable Diffusion baseline. We also show that the synthesized samples could be used to improve disease classifier performance for underrepresented subgroups through augmentation. Our code is accessible through the project website: https://parhamsaremi.github.io/rl4med-ddpo

Key facts. Cited by 5 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 24 of its 34 references that are in the map. First posted on arXiv 20 Mar 2025.

Builds on

24 of 34 references.

References · 24

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2017Proximal Policy Optimization Algorithmscited by 15,215
  4. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  5. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  6. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  7. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  8. 2022Classifier-Free Diffusion Guidancecited by 5,847
  9. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,626
  10. 2015Trust Region Policy Optimizationcited by 2,580
  11. 2023Training Diffusion Models with Reinforcement Learningcited by 982
  12. 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
12 more
  1. 2023DPOK: Reinforcement Learning for Fine-tuning Text-to-Image Diffusion Modelscited by 450
  2. 2019BCN20000: Dermoscopic Lesions in the Wildcited by 225
  3. 2020Deep Structural Causal Models for Tractable Counterfactual Inferencecited by 211
  4. 2022How well can Text-to-Image Generative Models understand Ethical Natural Language Interventions?cited by 92
  5. 2024Large-scale Reinforcement Learning for Diffusion Modelscited by 78
  6. 2023Deep Learning Approaches for Data Augmentation in Medical Imaging: A Reviewcited by 48
  7. 2023Analyzing Bias in Diffusion-based Face Generation Modelscited by 46
  8. 2018The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesionscited by 26
  9. 2025PRISM: High-Resolution & Precise Counterfactual Medical Image Generation using Language-guided Stable Diffusioncited by 17
  10. 2023Debiasing Counterfactuals In the Presence of Spurious Correlationscited by 12
  11. 2022Counterfactual Image Synthesis for Discovery of Personalized Predictive Image Markerscited by 10
  12. 2025Conditional Diffusion Models are Medical Image Classifiers that Provide Explainability and Uncertainty for Freecited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 4.

5 papers.

  1. 2025TauGenNet: Plasma-Driven Tau PET Image Synthesis via Text-Guided 3D Diffusion Modelscited by 1
  2. 2026Optimizing 3D Diffusion Models for Medical Imaging via Multi-Scale Reward Learningcited by 1
  3. 2026CRAFT: Clinical Reward-Aligned Finetuning for Medical Image Synthesiscited by 1
  4. 2026Reinforcement-Guided Synthetic Data Generation for Privacy-Sensitive Identity Recognitioncited by 0
  5. 2026Compositional Reward Models for Conditional Medical Image Generationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Med-R1: Reinforcement Learning for Generalizable Medical Reasoning in Vision-Language Models
  2. 2025MedVLM-R1: Incentivizing Medical Reasoning Capability of Vision-Language Models (VLMs) via Reinforcement Learning
  3. 2025Adaptive Reinforcement for Open-ended Medical Reasoning via Semantic-Guided Reward Collapse Mitigation
  4. 2025MedGround-R1: Advancing Medical Image Grounding via Spatial-Semantic Rewarded Group Relative Policy Optimization
  5. 2025Toward Effective Reinforcement Learning Fine-Tuning for Medical VQA in Vision-Language Models
  6. 2025MedReason-R1: Learning to Reason for CT Diagnosis with Reinforcement Learning and Local Zoom
  7. 2025MRG-R1: Reinforcement Learning for Clinically Aligned Medical Report Generation
  8. 2026MediX-R1: Open Ended Medical Reinforcement Learning