mlsanityData to 14 Oct 2026

Guided Flows for Generative Modeling and Decision Making

arXiv 2311.13443 ↗First posted 22 Nov 2023cs.LG cs.AI cs.CVcited by 101

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

Abstract (arXiv)

Classifier-free guidance is a key component for enhancing the performance of conditional generative models across diverse tasks. While it has previously demonstrated remarkable improvements for the sample quality, it has only been exclusively employed for diffusion models. In this paper, we integrate classifier-free guidance into Flow Matching (FM) models, an alternative simulation-free approach that trains Continuous Normalizing Flows (CNFs) based on regressing vector fields. We explore the usage of Guided Flows for a variety of downstream applications. We show that Guided Flows significantly improves the sample quality in conditional image generation and zero-shot text-to-speech synthesis, boasting state-of-the-art performance. Notably, we are the first to apply flow models for plan generation in the offline reinforcement learning setting, showcasing a 10x speedup in computation compared to diffusion models while maintaining comparable performance.

Key facts. Cited by 101 papers in the map (data through 14 Oct 2026). Placed in Flow matching, time series and science, one of 14 directions in Diffusion models. Builds on 45 of its 59 references that are in the map. First posted on arXiv 22 Nov 2023.

Builds on

45 of 59 references.

Closest ancestors · 4

Same direction, newest first

  1. 2023Training-free Linear Image Inverses via Flows25 Sep
  2. 2023Flow Matching in Latent Space17 Jul
  3. 2023Multisample Flow Matching: Straightening Flows with Minibatch Couplings28 Apr
  4. 2022Flow Matching for Generative Modeling6 Oct

Other references · 41

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  5. 2020Denoising Diffusion Implicit Modelscited by 9,781
  6. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  7. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  8. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  9. 2022Classifier-Free Diffusion Guidancecited by 5,847
  10. 2018Neural Ordinary Differential Equationscited by 3,779
  11. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,761
  12. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,838
29 more
  1. 2020Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problemscited by 1,920
  2. 2021Decision Transformer: Reinforcement Learning via Sequence Modelingcited by 1,546
  3. 2018Group Normalizationcited by 1,524
  4. 2020D4RL: Datasets for Deep Data-Driven Reinforcement Learningcited by 1,427
  5. 2022Planning with Diffusion for Flexible Behavior Synthesiscited by 1,061
  6. 2022Building Normalizing Flows with Stochastic Interpolantscited by 995
  7. 2022Denoising Diffusion Restoration Modelscited by 963
  8. 2022A Generalist Agentcited by 808
  9. 2023Neural Codec Language Models are Zero-Shot Text to Speech Synthesizerscited by 752
  10. 2021Offline Reinforcement Learning as One Big Sequence Modeling Problemcited by 644
  11. 2020WaveGrad: Estimating Gradients for Waveform Generationcited by 622
  12. 2022Diffusion Policies as an Expressive Policy Class for Offline Reinforcement Learningcited by 562
  13. 2022Is Conditional Generative Modeling all you need for Decision-Making?cited by 516
  14. 2023Voicebox: Text-Guided Multilingual Universal Speech Generation at Scalecited by 379
  15. 2017A Downsampled Variant of ImageNet as an Alternative to the CIFAR datasetscited by 377
  16. 2023Common Diffusion Noise Schedules and Sample Steps are Flawedcited by 310
  17. 2016Deep Reinforcement Learning for Dialogue Generationcited by 288
  18. 2018Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesiscited by 259
  19. 2022Multi-Game Decision Transformerscited by 214
  20. 2021RvS: What is Essential for Offline RL via Supervised Learning?cited by 185
  21. 2021Pretrained Transformers as Universal Computation Enginescited by 162
  22. 2019Reinforcement Learning Upside Down: Don't Predict Rewards -- Just Map Them to Actionscited by 125
  23. 2019Training Agents using Upside-Down Reinforcement Learningcited by 107
  24. 2019Reward-Conditioned Policiescited by 102
  25. 2019Improving Exploration in Soft-Actor-Critic with Normalizing Flows Policiescited by 38
  26. 2022Semi-Supervised Offline Reinforcement Learning with Action-Free Trajectoriescited by 28
  27. 2022Let Offline RL Flow: Training Conservative Agents in the Latent Space of Normalizing Flowscited by 21
  28. 2023Decision Stacks: Flexible Reinforcement Learning via Modular Generative Modelscited by 8
  29. 2022Reliable Conditioning of Behavioral Cloning for Offline Reinforcement Learningcited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 22; 2025: 52; 2026: 27.

101 papers.

Sort:

By area:

  1. 2025Improving Video Generation with Human Feedbackcited by 284
  2. 2024Adjoint Matching: Fine-tuning Flow and Diffusion Generative Models with Memoryless Stochastic Optimal Controlcited by 233
  3. 2025Flow Q-Learningcited by 184
  4. 2025Steering Your Diffusion Policy with Latent Space Reinforcement Learningcited by 169
  5. 2024Unlocking Guidance for Discrete State-Space Diffusion and Flow Modelscited by 129
  6. 2024Dirichlet Flow Matching with Applications to DNA Sequence Designcited by 115
  7. 2025Energy-Weighted Flow Matching for Offline Reinforcement Learningcited by 73
  8. 2024Affordance-based Robot Manipulation with Flow Matchingcited by 54
  9. 2025CFG-Zero*: Improved Classifier-Free Guidance for Flow Matching Modelscited by 52
  10. 2025On the Guidance of Flow Matchingcited by 45
  11. 2024Improved motif-scaffolding with SE(3) flow matchingcited by 43
  12. 2024Meta Flow Matching: Integrating Vector Fields on the Wasserstein Manifoldcited by 43
38 more
  1. 2024Conditional Wasserstein Distances with Applications in Bayesian OT Flow Matchingcited by 36
  2. 2024Diffusion World Model: Future Modeling Beyond Step-by-Step Rollout for Offline Reinforcement Learningcited by 31
  3. 2025La-Proteina: Atomistic Protein Generation via Partially Latent Flow Matchingcited by 30
  4. 2024ActionFlow: Equivariant, Accurate, and Efficient Policies with Spatially Symmetric Flow Matchingcited by 26
  5. 2024LAFMA: A Latent Flow Matching Model for Text-to-Audio Generationcited by 24
  6. 2025Flow Matching-Based Autonomous Driving Planning with Advanced Interactive Behavior Modelingcited by 22
  7. 2025CellFlux: Simulating Cellular Morphology Changes via Flow Matchingcited by 20
  8. 2024Stochastic Sampling from Deterministic Flow Modelscited by 18
  9. 2025Gen-DFL: Decision-Focused Generative Learning for Robust Decision Makingcited by 18
  10. 2024ParetoFlow: Guided Flows in Multi-Objective Optimizationcited by 17
  11. 2025DiverseFlow: Sample-Efficient Diverse Mode Coverage in Flowscited by 17
  12. 2024EquiJump: Protein Dynamics Simulation via SO(3)-Equivariant Stochastic Interpolantscited by 16
  13. 2025Feedback Guidance of Diffusion Modelscited by 16
  14. 2024Reflected Flow Matchingcited by 15
  15. 2024MusicFlow: Cascaded Flow Matching for Text Guided Music Generationcited by 15
  16. 2025Generative Models in Decision Making: A Surveycited by 15
  17. 2025Offline Model-Based Optimization: Comprehensive Reviewcited by 15
  18. 2025Normalizing Flows are Capable Models for Continuous Controlcited by 14
  19. 2024Geometric Representation Condition Improves Equivariant Molecule Generationcited by 13
  20. 2025Source-Guided Flow Matchingcited by 13
  21. 2024Multi-Modal and Multi-Attribute Generation of Single Cells with CFGencited by 12
  22. 2024Extended Flow Matching: a Method of Conditional Generation with Generalized Continuity Equationcited by 11
  23. 2025Nabla-R2D3: Effective and Efficient 3D Diffusion Alignment with 2D Rewardscited by 11
  24. 2024Bespoke Non-Stationary Solvers for Fast Sampling of Diffusion and Flow Modelscited by 10
  25. 2025Multi-agent Coordination via Flow Matchingcited by 10
  26. 2024F3low: Frame-to-Frame Coarse-grained Molecular Dynamics with SE(3) Guided Flow Matchingcited by 9
  27. 2025Learning of Population Dynamics: Inverse Optimization Meets JKO Schemecited by 9
  28. 2025Controlled Generation with Equivariant Variational Flow Matchingcited by 9
  29. 2025Guided Flow Policy: Learning from High-Value Actions in Offline Reinforcement Learningcited by 9
  30. 2025Unleashing Flow Policies with Distributional Criticscited by 8
  31. 2025ARFlow: Human Action-Reaction Flow Matching with Physical Guidancecited by 7
  32. 2026Compositional Planning with Jumpy World Modelscited by 7
  33. 2025Audio synthesizer inversion in symmetric parameter spaces with approximately equivariant flow matchingcited by 6
  34. 2025Prior-Guided Flow Matching for Target-Aware Molecule Design with Learnable Atom Numbercited by 6
  35. 2025Discrete Guidance Matching: Exact Guidance for Discrete Flow Matchingcited by 6
  36. 2025Expressive Value Learning for Scalable Offline Reinforcement Learningcited by 6
  37. 2026GlyphPrinter: Region-Grouped Direct Preference Optimization for Glyph-Accurate Visual Text Renderingcited by 6
  38. 2025UniConFlow: A Unified Constrained Flow-Matching Framework for Certified Motion Planningcited by 5

50 most cited of 101 All 101 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026A Survey of Flow Matching in Reinforcement Learning
  2. 2025Flow Matching Policy Gradients
  3. 2026How to Guide Your Flow: Few-Step Alignment via Flow Map Reward Guidance
  4. 2026Momentum Guidance: Plug-and-Play Guidance for Flow Models
  5. 2023Improving and generalizing flow-based generative models with minibatch optimal transport
  6. 2025FlowQ: Energy-Guided Flow Policies for Offline Reinforcement Learning
  7. 2025Designing a Conditional Prior Distribution for Flow-Based Generative Models
  8. 2026ODE-free Neural Flow Matching for One-Step Generative Modeling