mlsanityData to 7 Oct 2026

Continuous Adversarial Flow Models

arXiv 2604.11521 ↗First posted 13 Apr 2026cs.LG cs.CVcited by 4

On the map: Diffusion models → Flow matching, time series and science

Abstract (arXiv)

We propose continuous adversarial flow models, a type of continuous-time flow model trained with an adversarial objective. Unlike flow matching, which uses a fixed mean-squared-error criterion, our approach introduces a learned discriminator to guide training. This change in objective induces a different generalized distribution, which empirically produces samples that are better aligned with the target data distribution. Our method is primarily proposed for post-training existing flow-matching models, although it can also train models from scratch. On the ImageNet 256px generation task, our post-training substantially improves the guidance-free FID of latent-space SiT from 8.26 to 3.63 and of pixel-space JiT from 7.17 to 3.57. It also improves guided generation, reducing FID from 2.06 to 1.53 for SiT and from 1.86 to 1.80 for JiT. We further evaluate our approach on text-to-image generation, where it achieves improved results on both the GenEval and DPG benchmarks.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Placed in Flow matching, time series and science, one of 14 directions in Diffusion models. Builds on 77 of its 85 references that are in the map. First posted on arXiv 13 Apr 2026.

Builds on

77 of 85 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025Terminal Velocity Matching24 Nov
  2. 2023Flow Matching on General Geometries7 Feb
  3. 2022Flow Matching for Generative Modeling6 Oct
  4. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow7 Sep

Other references · 73

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  4. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  5. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  6. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  7. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  8. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  9. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  10. 2022Scalable Diffusion Models with Transformerscited by 5,931
  11. 2022Classifier-Free Diffusion Guidancecited by 5,717
  12. 2016Layer Normalizationcited by 5,579
38 more
  1. 2018Neural Ordinary Differential Equationscited by 3,733
  2. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  3. 2016Improved Techniques for Training GANscited by 2,938
  4. 2017Improved Training of Wasserstein GANscited by 2,223
  5. 2019Root Mean Square Layer Normalizationcited by 1,425
  6. 2020Training Generative Adversarial Networks with Limited Datacited by 1,184
  7. 2016Least Squares Generative Adversarial Networkscited by 1,000
  8. 2023GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignmentcited by 946
  9. 2025Emerging Properties in Unified Multimodal Pretrainingcited by 855
  10. 2016Training Deep Nets with Sublinear Memory Costcited by 825
  11. 2023Adversarial Diffusion Distillationcited by 741
  12. 2024SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformerscited by 707
  13. 2018Which Training Methods for GANs do actually Converge?cited by 672
  14. 2024Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Thinkcited by 666
  15. 2024Improved Distribution Matching Distillation for Fast Image Synthesiscited by 648
  16. 2023PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallelcited by 641
  17. 2016f-GAN: Training Generative Neural Samplers using Variational Divergence Minimizationcited by 504
  18. 2022StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasetscited by 489
  19. 2017Towards Principled Methods for Training Generative Adversarial Networkscited by 460
  20. 2024ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignmentcited by 455
  21. 2023Simple diffusion: End-to-end diffusion for high resolution imagescited by 413
  22. 2023Common Diffusion Noise Schedules and Sample Steps are Flawedcited by 308
  23. 2024Guiding a Diffusion Model with a Bad Version of Itselfcited by 286
  24. 2024Fast High-Resolution Image Synthesis with Latent Adversarial Diffusion Distillationcited by 276
  25. 2024Simplifying, Stabilizing and Scaling Continuous-Time Consistency Modelscited by 276
  26. 2025Diffusion Transformers with Representation Autoencoderscited by 275
  27. 2024SDXL-Lightning: Progressive Adversarial Diffusion Distillationcited by 258
  28. 2025Seedance 1.0: Exploring the Boundaries of Video Generation Modelscited by 247
  29. 2025Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformercited by 247
  30. 2018The relativistic discriminator: a key element missing from standard GANcited by 234
  31. 2025Seedream 4.0: Toward Next-generation Multimodal Image Generationcited by 233
  32. 2017Geometric GANcited by 232
  33. 2022Riemannian Score-Based Generative Modellingcited by 216
  34. 2023UFOGen: You Forward Once Large Scale Text-to-Image Generation via Diffusion GANscited by 165
  35. 2024Hyper-SD: Trajectory Segmented Consistency Model for Efficient Image Synthesiscited by 153
  36. 2020Riemannian Continuous Normalizing Flowscited by 143
  37. 2025Diffusion Adversarial Post-Training for One-Step Video Generationcited by 142
  38. 2021Generative Adversarial Transformerscited by 120

50 most cited of 73 All 73 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026Causal-rCM: A Unified Teacher-Forcing and Self-Forcing Open Recipe for Autoregressive Diffusion Distillation in Streaming Video Generation and Interactive World Modelscited by 23
  2. 2026On-Policy Adversarial Flow Distillation for Autoregressive Video Generationcited by 2
  3. 2026Three-Body Scattering for Generative Modelingcited by 2
  4. 2026Amortized Moment Matching for Visual Generationcited by 2

Similar, not cited

Close in wording, no citation either way

  1. 2025Align Your Flow: Scaling Continuous-Time Flow Map Distillation
  2. 2024Self-Corrected Flow Distillation for Consistent One-Step and Few-Step Text-to-Image Generation
  3. 2026FAIL: Flow Matching Adversarial Imitation Learning for Image Generation
  4. 2023Multisample Flow Matching: Straightening Flows with Minibatch Couplings
  5. 2023Flow Matching in Latent Space
  6. 2025FlowPure: Continuous Normalizing Flows for Adversarial Purification
  7. 2025A Theoretical Analysis of Discrete Flow Matching Generative Models
  8. 2025Distribution Matching via Generalized Consistency Models