mlsanityData to 14 Oct 2026

DiverseFlow: Sample-Efficient Diverse Mode Coverage in Flows

arXiv 2504.07894 ↗First posted 10 Apr 2025cs.LGcited by 17

Not on the map. Why?

Abstract (arXiv)

Many real-world applications of flow-based generative models desire a diverse set of samples that cover multiple modes of the target distribution. However, the predominant approach for obtaining diverse sets is not sample-efficient, as it involves independently obtaining many samples from the source distribution and mapping them through the flow until the desired mode coverage is achieved. As an alternative to repeated sampling, we introduce DiverseFlow: a training-free approach to improve the diversity of flow models. Our key idea is to employ a determinantal point process to induce a coupling between the samples that drives diversity under a fixed sampling budget. In essence, DiverseFlow allows exploration of more variations in a learned flow model with fewer samples. We demonstrate the efficacy of our method for tasks where sample-efficient diversity is desirable, such as text-guided image generation with polysemous words, inverse problems like large-hole inpainting, and class-conditional image synthesis.

Key facts. Cited by 17 papers in the map (data through 14 Oct 2026). Builds on 28 of its 35 references that are in the map. First posted on arXiv 10 Apr 2025.

Builds on

28 of 35 references.

References · 28

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  4. 2020Denoising Diffusion Implicit Modelscited by 9,781
  5. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  6. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  7. 2022Classifier-Free Diffusion Guidancecited by 5,847
  8. 2022Flow Matching for Generative Modelingcited by 5,702
  9. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,181
  10. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,700
  11. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 3,045
  12. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,988
16 more
  1. 2019Improved Precision and Recall Metric for Assessing Generative Modelscited by 944
  2. 2023Stochastic Interpolants: A Unifying Framework for Flows and Diffusionscited by 939
  3. 2023Improving and generalizing flow-based generative models with minibatch optimal transportcited by 879
  4. 2021Tackling the Generative Learning Trilemma with Denoising Diffusion GANscited by 516
  5. 2022Improving Diffusion Models for Inverse Problems using Manifold Constraintscited by 508
  6. 2016Stein Variational Gradient Descent: A General Purpose Bayesian Inference Algorithmcited by 507
  7. 2022Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Modelscited by 424
  8. 2021General Facial Representation Learning in a Visual-Linguistic Mannercited by 195
  9. 2023Flow Matching in Latent Spacecited by 160
  10. 2022Multi-Objective GFlowNetscited by 101
  11. 2023Guided Flows for Generative Modeling and Decision Makingcited by 101
  12. 2023Simulation-free Schr"odinger bridges via score and flow matchingcited by 83
  13. 2019Diverse Trajectory Forecasting with Determinantal Point Processescited by 80
  14. 2023Particle Guidance: non-I.I.D. Diverse Sampling with Diffusion Modelscited by 71
  15. 2024Immiscible Diffusion: Accelerating Diffusion Training with Noise Assignmentcited by 14
  16. 2024Extended Flow Matching: a Method of Conditional Generation with Generalized Continuity Equationcited by 11

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 7; 2026: 10.

17 papers.

Sort:

By area:

  1. 2025It's Never Too Late: Noise Optimization for Collapse Recovery in Trained Diffusion Modelscited by 11
  2. 2026Verifier-Constrained Flow Expansion for Discovery Beyond the Datacited by 7
  3. 2026Free Lunch for Pass@k? Low Cost Diverse Sampling for Diffusion Language Modelscited by 5
  4. 2025Quantum latent distributions in deep generative modelscited by 3
  5. 2025Letting Trajectories Spread: Quality-Preserving Control for Diverse Flow Matchingcited by 3
  6. 2025GRASP: Guided Residual Adapters with Sample-wise Partitioningcited by 2
  7. 2026AutoWorld: Learning Multi-Agent Traffic Simulation with Self-Supervised World Modelscited by 2
  8. 2026Inference-Time Attribute Distribution Alignment for Unconditional Diffusioncited by 2
  9. 2025Inference-Time Compute Scaling For Flow Matchingcited by 1
  10. 2025Diversifying Long Prompt Image Generation through Structured Prompt Embedding Space Samplingcited by 1
  11. 2026Consistency-Preserving Diverse Video Generationcited by 1
  12. 2026Initialization is Half the Battle: Generating Diverse Images from a Guidance Potential Posteriorcited by 1
5 more
  1. 2025Score-Regularized Joint Sampling with Importance Weights for Flow Matchingcited by 0
  2. 2026Diverse Sampling in Diffusion Models with Marginal Preserving Particle Guidancecited by 0
  3. 2026Flow Matching with Optimized Subclass Priors for Medical Image Augmentationcited by 0
  4. 2026Breaking the Lock-in: Diversifying Text-to-Image Generation via Representation Modulationcited by 0
  5. 2026JIVE: Jacobian-Informed Volume Expansion for Diverse Generative Samplingcited by 0