mlsanityData to 7 Oct 2026

Contrastive Flow Matching

arXiv 2506.05350 ↗First posted 5 Jun 2025cs.CVcited by 29

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

Abstract (arXiv)

Unconditional flow-matching trains diffusion models to transport samples from a source distribution to a target distribution by enforcing that the flows between sample pairs are unique. However, in conditional settings (e.g., class-conditioned models), this uniqueness is no longer guaranteed--flows from different conditions may overlap, leading to more ambiguous generations. We introduce Contrastive Flow Matching, an extension to the flow matching objective that explicitly enforces uniqueness across all conditional flows, enhancing condition separation. Our approach adds a contrastive objective that maximizes dissimilarities between predicted flows from arbitrary sample pairs. We validate Contrastive Flow Matching by conducting extensive experiments across varying model architectures on both class-conditioned (ImageNet-1k) and text-to-image (CC3M) benchmarks. Notably, we find that training models with Contrastive Flow Matching (1) improves training speed by a factor of up to 9x, (2) requires up to 5x fewer de-noising steps and (3) lowers FID by up to 8.9 compared to training the same models with flow matching. We release our code at: https://github.com/gstoica27/DeltaFM.git.

Key facts. Cited by 29 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 36 of its 46 references that are in the map. First posted on arXiv 5 Jun 2025.

Builds on

36 of 46 references.

Closest ancestors · 2

Same direction, newest first

  1. 2022Flow Matching for Generative Modeling6 Oct
  2. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow7 Sep

Other references · 34

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  4. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  5. 2020Denoising Diffusion Implicit Modelscited by 9,655
  6. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  7. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  8. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  9. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  10. 2022Classifier-Free Diffusion Guidancecited by 5,717
  11. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,094
  12. 2018Neural Ordinary Differential Equationscited by 3,733
22 more
  1. 2016Improved Techniques for Training GANscited by 2,938
  2. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,833
  3. 2022Diffusion Posterior Sampling for General Noisy Inverse Problemscited by 1,375
  4. 2023One-step Diffusion with Distribution Matching Distillationcited by 978
  5. 2022Building Normalizing Flows with Stochastic Interpolantscited by 964
  6. 2019Improved Precision and Recall Metric for Assessing Generative Modelscited by 925
  7. 2023Stochastic Interpolants: A Unifying Framework for Flows and Diffusionscited by 897
  8. 2023Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inferencecited by 826
  9. 2024SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformerscited by 707
  10. 2024Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Thinkcited by 666
  11. 2024Improved Distribution Matching Distillation for Fast Image Synthesiscited by 648
  12. 2021Score-based Generative Modeling in Latent Spacecited by 634
  13. 2022All are Worth Words: A ViT Backbone for Diffusion Modelscited by 498
  14. 2024Guiding a Diffusion Model with a Bad Version of Itselfcited by 286
  15. 2021Generating Images with Sparse Representationscited by 262
  16. 2024Applying Guidance in a Limited Interval Improves Sample and Distribution Quality in Diffusion Modelscited by 240
  17. 2023Contrastive Energy Prediction for Exact Energy-Guided Diffusion Sampling in Offline Reinforcement Learningcited by 145
  18. 2024CFG++: Manifold-constrained Classifier Free Guidance for Diffusion Modelscited by 138
  19. 2024Dynamic Negative Guidance of Diffusion Modelscited by 28
  20. 2024Improving image synthesis with diffusion-negative samplingcited by 8
  21. 2024Gradient-Free Classifier Guidance for Diffusion Model Samplingcited by 8
  22. 2017TripletGAN: Training Generative Model with Triplet Losscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 10; 2026: 19.

29 papers.

Sort:

By area:

  1. 2026Generative Modeling via Driftingcited by 98
  2. 2025There is No VAE: End-to-End Pixel-Space Generative Modeling via Self-Supervised Pre-trainingcited by 23
  3. 2025Unified Multi-Modal Interactive & Reactive 3D Motion Generation via Rectified Flowcited by 6
  4. 2025Learning by Neighbor-Aware Semantics, Deciding by Open-form Flows: Towards Robust Zero-Shot Skeleton Action Recognitioncited by 3
  5. 2026OmniCustom: Sync Audio-Video Customization Via Joint Audio-Video Generation Modelcited by 3
  6. 2025TimeFlow: Towards Stochastic-Aware and Efficient Time Series Generation via Flow Matching Modelingcited by 2
  7. 2026EditYourself: Audio-Driven Generation and Manipulation of Talking Head Videos with Diffusion Transformerscited by 2
  8. 2026MPDiT: Multi-Patch Global-to-Local Transformer Architecture For Efficient Flow Matching and Diffusion Modelcited by 2
  9. 2025VeCoR -- Velocity Contrastive Regularization for Flow Matchingcited by 1
  10. 2025WeMMU: Enhanced Bridging of Vision-Language Models and Diffusion Models via Noisy Query Tokenscited by 1
  11. 2025Speedrunning ImageNet Diffusioncited by 1
  12. 2025MixFlow Training: Alleviating Exposure Bias with Slowed Interpolation Mixturecited by 1
17 more
  1. 2026Improving Diffusion Generalization with Weak-to-Strong Segmented Guidancecited by 1
  2. 2026High-Fidelity One-Step Generative Visuomotor Policy via Recursive Correction, Frequency Consistency, and Contrastive Flow Matchingcited by 1
  3. 2025Align Your Tangent: Training Better Consistency Models via Manifold-Aligned Tangentscited by 0
  4. 2025On the continuity of flowscited by 0
  5. 2026Beyond Fixed Inference: Quantitative Flow Matching for Adaptive Image Denoisingcited by 0
  6. 2026Posterior Augmented Flow Matchingcited by 0
  7. 2026Flow Matching with Arbitrary Auxiliary Pathscited by 0
  8. 2026PG-LRF: Physiology-Guided Latent Rectified Flow for Electro-Hemodynamic PPG-to-ECG Generationcited by 0
  9. 2026Machine Unlearning for Masked Diffusion Language Modelscited by 0
  10. 2026RobustSpeechFlow: Learning Robust Text-to-Speech Trajectories via Augmentation-based Contrastive Flow Matchingcited by 0
  11. 2026Contrastive-Augmented Flow Matching for Style-Content Disentanglementcited by 0
  12. 2026Revisiting Spectral Representations in Generative Diffusion Modelscited by 0
  13. 2026Beyond Random Couplings: Contrastive Noise Alignment in Generative Flowscited by 0
  14. 2026CARF: Contrastive Attraction-Repulsion of Failure-Guided Flow Matchingcited by 0
  15. 2026On the spectral properties of generative denoiser Jacobianscited by 0
  16. 2026Online Evolution Strategy for Flow-Matching VLA Policies via Self-Supervised Trajectory Distribution Optimizationcited by 0
  17. 2026Smoother Flow Matching via Contrastive Trajectory Repulsioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Better Source, Better Flow: Learning Condition-Dependent Source Distribution for Flow Matching
  2. 2025Flow Matching in the Low-Noise Regime: Pathologies and a Contrastive Remedy
  3. 2026Difficulty-Calibrated Interpolation Paths for Conditional Flow Matching
  4. 2026SubFlow: Sub-mode Conditioned Flow Matching for Diverse One-Step Generation
  5. 2024Flow Matching Posterior Sampling: A Training-free Conditional Generation for Flow Matching
  6. 2025CAR-Flow: Condition-Aware Reparameterization Aligns Source and Target for Better Flow Matching
  7. 2023Flow Matching in Latent Space
  8. 2024Discrete Flow Matching