CONFLUX: A Latent Diffusion Model for 3D Chest-CT Synthesis with RL Post-Training
On the map: Diffusion models → Medical imaging and segmentation
Abstract (arXiv)
Controllable generative models of 3D medical images can synthesize volumes with specified clinical attributes, but this demands samples that are simultaneously high-fidelity, natively 3D, and faithful to the requested conditioning. We present CONFLUX, a latent diffusion model for chest computed tomography (CT): a 3D variational autoencoder compresses each volume, and a rectified-flow transformer generates in the latent space. Generation is conditioned on structured radiological metadata (18 abnormality findings, sex, age, and reconstruction kernel) through adaptive layer normalization. The model leads strong volumetric baselines on tri-planar Frechet distance (FID 32.3 vs. 74.6 for MAISI) while exposing direct control over clinical attributes. To strengthen that control we add an online reinforcement-learning post-training stage (group-relative policy optimization) that rewards how reliably a classifier recovers the requested findings from each generated volume. Judged by a separate, independent classifier, post-training removes 47% of the shortfall relative to real-scan reliability. We release the model and a ~200k synthetic chest-CT dataset with conditioning metadata spanning a wide variety of clinical findings.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models. Builds on 20 of its 21 references that are in the map. First posted on arXiv 3 Jul 2026.
Builds on
20 of 21 references.
Closest ancestors · 5
Same direction, newest first
- 2026BrainG3N: A Dual-Purpose Tokenizer for Controllable 3D Brain MRI Generation17 Jun
- 20243D MedDiffusion: A 3D Medical Latent Diffusion Model for Controllable and High-quality Medical Image Generation17 Dec
- 2024MAISI: Medical AI for Synthetic Imaging13 Sep
- 2023GenerateCT: Text-Conditional Generation of 3D Chest CT Volumes25 May
- 2022Brain Imaging Generation with Latent Diffusion Models15 Sep
Other references · 15
- 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
- 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
- 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
- 2022Scalable Diffusion Models with Transformerscited by 6,054
- 2022Classifier-Free Diffusion Guidancecited by 5,847
- 2022Flow Matching for Generative Modelingcited by 5,702
- 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,181
- 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,700
- 2023Training Diffusion Models with Reinforcement Learningcited by 982
- 2025Flow-GRPO: Training Flow Matching Models via Online RLcited by 661
- 2023DPOK: Reinforcement Learning for Fine-tuning Text-to-Image Diffusion Modelscited by 450
- 2020Reliable Fidelity and Diversity Metrics for Generative Modelscited by 434
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025LAND: Lung and Nodule Diffusion for 3D Chest CT Synthesis with Anatomical Guidance
- 2024Multi-Conditioned Denoising Diffusion Probabilistic Model (mDDPM) for Medical Image Synthesis
- 2026The Learnability Gap in Medical Latent Diffusion
- 2026Controllable Lung Nodule Synthesis via Histogram-Regularized Latent Diffusion Models
- 2026Pixel-Level Residual Diffusion Transformer: Scalable 3D CT Volume Generation
- 2025MedLoRD: A Medical Low-Resource Diffusion Model for High-Resolution 3D CT Image Synthesis
- 2023Cascaded Latent Diffusion Models for High-Resolution Chest X-ray Synthesis
- 2025Anatomy-Grounded Weakly Supervised Prompt Tuning for Chest X-ray Latent Diffusion Models