mlsanityData to 7 Oct 2026

Particle Guidance: non-I.I.D. Diverse Sampling with Diffusion Models

arXiv 2310.13102 ↗First posted 19 Oct 2023cs.LG cs.AIcited by 65

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

In light of the widespread success of generative models, a significant amount of research has gone into speeding up their sampling time. However, generative models are often sampled multiple times to obtain a diverse set incurring a cost that is orthogonal to sampling time. We tackle the question of how to improve diversity and sample efficiency by moving beyond the common assumption of independent samples. We propose particle guidance, an extension of diffusion-based generative sampling where a joint-particle time-evolving potential enforces diversity. We analyze theoretically the joint distribution that particle guidance generates, how to learn a potential that achieves optimal diversity, and the connections with methods in other disciplines. Empirically, we test the framework both in the setting of conditional image generation, where we are able to increase diversity without affecting quality, and molecular conformer generation, where we reduce the state-of-the-art median error by 13% on average.

Key facts. Cited by 65 papers in the map (data through 7 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 33 of its 50 references that are in the map. First posted on arXiv 19 Oct 2023.

Builds on

33 of 50 references.

Closest ancestors · 10

Same direction, newest first

  1. 2023Restart Sampling for Improving Generative Processes26 Jun
  2. 2023Reduce, Reuse, Recycle: Compositional Generation with Energy-Based Diffusion Models and MCMC22 Feb
  3. 2022From Denoising Diffusions to Denoising Markov Models7 Nov
  4. 2022Sampling is as easy as learning the score: theory for diffusion models with minimal data assumptions22 Sep
  5. 2022Classifier-Free Diffusion Guidance26 Jul
  6. 2022Elucidating the Design Space of Diffusion-Based Generative Models1 Jun
  7. 2022Riemannian Score-Based Generative Modelling6 Feb
  8. 2021High-Resolution Image Synthesis with Latent Diffusion Models20 Dec
  9. 2021Diffusion Models Beat GANs on Image Synthesis11 May
  10. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov

Other references · 23

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  3. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  4. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,131
  5. 2021CLIPScore: A Reference-free Evaluation Metric for Image Captioningcited by 2,388
  6. 2022GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generationcited by 511
  7. 2016Stein Variational Gradient Descent: A General Purpose Bayesian Inference Algorithmcited by 498
  8. 2022Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Modelscited by 418
  9. 2022DiffDock: Diffusion Steps, Twists, and Turns for Molecular Dockingcited by 307
  10. 2022Torsional Diffusion for Molecular Conformer Generationcited by 262
  11. 2020GEOM: Energy-annotated molecular conformations for property prediction and molecular generationcited by 238
  12. 2023SE(3) diffusion model with application to protein backbone generationcited by 214
11 more
  1. 2021Learning Gradient Fields for Molecular Conformation Generationcited by 162
  2. 2021GeoMol: Torsional Geometric Generation of Molecular 3D Conformer Ensemblescited by 106
  3. 2022Poisson Flow Generative Modelscited by 95
  4. 2023PFGM++: Unlocking the Potential of Physics-Inspired Generative Modelscited by 73
  5. 2020Optimal dimension dependence of the Metropolis-Adjusted Langevin Algorithmcited by 57
  6. 2017Message Passing Stein Variational Gradient Descentcited by 47
  7. 2020Blindness of score-based methods to isolated components and mixing proportionscited by 33
  8. 2021Annealed Stein Variational Gradient Descentcited by 24
  9. 2018Stochastic Particle-Optimization Sampling and the Non-Asymptotic Convergence Theorycited by 20
  10. 2020Kernel Stein Generative Modelingcited by 5
  11. 2023Modeling Molecular Structures with Intrinsic Diffusion Modelscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 13; 2025: 24; 2026: 26.

65 papers.

Sort:

By area:

  1. 2024Particle Denoising Diffusion Samplercited by 63
  2. 2024Good Seed Makes a Good Crop: Discovering Secret Seeds in Text-to-Image Diffusion Modelscited by 47
  3. 2025One-step Diffusion Models with f-Divergence Distribution Matchingcited by 43
  4. 2024Consistency-diversity-realism Pareto fronts of conditional image generative modelscited by 35
  5. 2025Cultivating Pluralism In Algorithmic Monoculture: The Community Alignment Datasetcited by 32
  6. 2024Shielded Diffusion: Generating Novel and Diverse Images using Sparse Repellencycited by 21
  7. 2024Minority-Focused Text-to-Image Generation via Prompt Optimizationcited by 18
  8. 2025Action-Minimization Meets Generative Modeling: Efficient Transition Path Sampling with the Onsager-Machlup Functionalcited by 18
  9. 2025NExT-Mol: 3D Diffusion Meets 1D Language Modeling for 3D Molecule Generationcited by 17
  10. 2025DiverseFlow: Sample-Efficient Diverse Mode Coverage in Flowscited by 17
  11. 2023Correcting Diffusion Generation through Resamplingcited by 15
  12. 2024Repulsive Latent Score Distillation for Solving Inverse Problemscited by 15
38 more
  1. 2025SPARKE: Scalable Prompt-Aware Diversity and Novelty Guidance in Diffusion Models via RKE Scorecited by 14
  2. 2026VLS: Steering Pretrained Robot Policies via Vision-Language Modelscited by 14
  3. 2025Applications of Modular Co-Design for De Novo 3D Molecule Generationcited by 13
  4. 2024ProCreate, Don't Reproduce! Propulsive Energy Diffusion for Creative Generationcited by 12
  5. 2025Provable Maximum Entropy Manifold Exploration via Diffusion Modelscited by 12
  6. 2024Motion Modes: What Could Happen Next?cited by 11
  7. 2025Scaling Group Inference for Diverse and High-Quality Generationcited by 11
  8. 2023DreamDistribution: Learning Prompt Distribution for Diverse In-distribution Generationcited by 10
  9. 2024Conformal Generative Modeling with Improved Sample Efficiency through Sequential Greedy Filteringcited by 10
  10. 2025Diverse Text-to-Image Generation via Contrastive Noise Optimizationcited by 10
  11. 2025It's Never Too Late: Noise Optimization for Collapse Recovery in Trained Diffusion Modelscited by 9
  12. 2024Diffusion Bridge AutoEncoders for Unsupervised Representation Learningcited by 6
  13. 2024Conditional Vendi Score: Prompt-Aware Diversity Evaluation for Generative AI Models and LLMscited by 6
  14. 2025Increasing the Utility of Synthetic Images through Chamfer Guidancecited by 6
  15. 2026Verifier-Constrained Flow Expansion for Discovery Beyond the Datacited by 6
  16. 2024CoCoG: Controllable Visual Stimuli Generation based on Human Concept Representationscited by 5
  17. 2024Stiefel Flow Matching for Moment-Constrained Structure Elucidationcited by 5
  18. 2025Boost-and-Skip: A Simple Guidance-Free Diffusion for Minority Generationcited by 5
  19. 2025DIMCIM: A Quantitative Evaluation Framework for Default-mode Diversity and Generalization in Text-to-Image Generative Modelscited by 4
  20. 2025Tree-Guided Diffusion Plannercited by 4
  21. 2025Cross-fluctuation phase transitions reveal sampling dynamics in diffusion modelscited by 4
  22. 2025Letting Trajectories Spread: Quality-Preserving Control for Diverse Flow Matchingcited by 3
  23. 2025LoRAverse: A Submodular Framework to Retrieve Diverse Adapters for Diffusion Modelscited by 3
  24. 2025TPSO: Training-Free Diverse Image Generation via Semantic Prompt Embedding Optimizationcited by 3
  25. 2026Time-Annealed Perturbation Sampling: Diverse Generation for Diffusion Language Modelscited by 3
  26. 2026DAK-UCB: Diversity-Aware Prompt Routing for LLMs and Generative Modelscited by 2
  27. 2026Inference-Time Attribute Distribution Alignment for Unconditional Diffusioncited by 2
  28. 2025Stein Diffusion Guidance: Training-Free Posterior Correction for Sampling Beyond High-Density Regionscited by 1
  29. 2025Inference-Time Compute Scaling For Flow Matchingcited by 1
  30. 2025Diversifying Long Prompt Image Generation through Structured Prompt Embedding Space Samplingcited by 1
  31. 2026Exposing Diversity Bias in Deep Generative Models: Statistical Origins and Correction of Diversity Errorcited by 1
  32. 2026Consistency-Preserving Diverse Video Generationcited by 1
  33. 2026STRIDE: Training-Free Diversity Guidance via PCA-Directed Feature Perturbation in Single-Step Diffusion Modelscited by 1
  34. 2026Variance-Tilted Diffusion Models for Diverse Samplingcited by 1
  35. 2026Don't Settle at the Mode! Mitigating Diversity Collapse in Pretrained Flow Models via Feature Self-Guidancecited by 1
  36. 2026Exploring More to Solve More: Boosting Diversity in Text Diffusion Models via Entropy-Based Guidancecited by 1
  37. 2025A Gradient Flow Approach to Solving Inverse Problems with Latent Diffusion Modelscited by 0
  38. 2025Score-Regularized Joint Sampling with Importance Weights for Flow Matchingcited by 0

50 most cited of 65 All 65 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Greed is Good: A Unifying Perspective on Guided Generation
  2. 2024Context-Guided Diffusion for Out-of-Distribution Molecular and Protein Design
  3. 2025Diffusion Models with Double Guidance: Generate with aggregated datasets
  4. 2026On the Robustness of Distribution Support under Diffusion Guidance
  5. 2024Theoretical Insights for Diffusion Guidance: A Case Study for Gaussian Mixture Models
  6. 2026Best-of-N Guidance for Test-time Diffusion Alignment
  7. 2024Compress Guidance in Conditional Diffusion Sampling
  8. 2023Practical and Asymptotically Exact Conditional Sampling in Diffusion Models