mlsanityData to 7 Oct 2026

Flow matching, time series and science

1,679 papers16 this weekLow confidence in this grouping: the papers may belong to more than one topic, or the group may changeLow confidence in this grouping: the papers may belong to more than one topic, or the group may change · About

Keywords: flow, diffusion, matching, flow matching, generative

Key facts. Flow matching, time series and science: 1,679 papers on arXiv since 2020 (data through 7 Oct 2026). 626 of its 1,679 mapped papers (37%) cite “Flow Matching for Generative Modeling” (2022, arXiv 2210.02747). 495 of its 1,679 mapped papers (29%) cite “Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow” (2022, arXiv 2209.03003). 100 new papers 17 Sep–7 Oct.

What’s new

17 Sep – 7 Oct 2026

100 new papers, 17 Sep – 7 Oct; 16 this week.

  1. This week · 16
  2. Velocity Scaling in Flow Matching
  3. Conditional Flow Matching for Generation of 3D Multi-variable Instantaneous Urban Microclimate Fields
  4. Efficient Patch-Based Anomaly Detection Fused with Diffusion Driven Generative Modeling for Semiconductor Wafer Bin Map Open Set Anomaly Detection also fits: Diffusion foundations and sampling
  5. EC-EarthFlow: Probabilistic emulation of daily transient global climate model simulations with flow matching
  6. Domain-informed Adaptive Sampling for Generalizable PINNs in Metal Additive Manufacturing via Conditional Flow Matching
  7. Co-Evolving Paths and Flows via Path-Flow Alignment
  8. Steering Diffusion Models to Rare Events with Sequential Monte Carlo
  9. FlowCF: Sparse Counterfactual Explanations for Mixed-Type Tabular Data using Flow Matching
  10. Cylindrical Geodesic Flow Matching for Quasiperiodic Physiological Signal Transformation also fits: Audio, speech and music
  11. Sensor Geometry as a Flow-Matching Prior for Multi-Channel Brain Signals
All 100
  1. Conditional Flow Matching for Transport Between Markov Processes
  2. Direct Intermediate Initialization for Tilted Diffusion Samplers also fits: Diffusion foundations and sampling
  3. Conditional Flow Matching for Single-Neuron Electrophysiology: Capturing Multimodal Responses Across Stimuli
  4. Latent Flow Matching for Molecular Graph Generation
  5. MercerFlow: Flow Matching in a Kernel-Induced Latent Space for Probabilistic Forecasting
  6. Beyond Transport Cost: Routing Differences between Flow Matching and Optimal Transport
  7. Earlier · 84
  8. Inference-Time Projection for Physically Valid Biomolecular Diffusion Models
  9. LiFT: Loop Flow Transformers also fits: Image generation, text-to-image and editing
  10. Universality and Convergence of Generative Flows also fits: Diffusion foundations and sampling
  11. Efficient Graph Generation via Direct Prediction and Flow Matching
  12. Hybrid-Basis Feature Forecasting for Diffusion Sampling Acceleration also fits: Diffusion foundations and sampling
  13. EDISCO: Equivariant DIScrete Diffusion for Euclidean Combinatorial Optimization
  14. TempoBridge: Source-Conditioned Flow Matching with Optimal Transport Couplings for Single-Cell Population Transitions
  15. Backward-Consistent Diffusion Sampling for Sparsely Observed PDE Inverse Problems also fits: Diffusion foundations and sampling
  16. ManifoldCache: Training-Free Diffusion Acceleration via Constraint Manifold Caching
  17. Reinforcement Learning on the Discrete Composition Channel of a Crystal Generator: Validated Gains and Reward Hacking
  18. Getting Your Guidance Weights Right in diffusion and flow-matching posterior sampling also fits: Diffusion foundations and sampling
  19. AREX: Affine-Residual Exponential Integrator for Few-Step Sampling in Flow Matching
  20. A Unified Framework for Bayesian Data Assimilation with Generative Models and Observation Interpolants
  21. DAWIS: Data Assimilation with Windowed Inverse Sampling via Multitask Interpolants
  22. Learn Feasibility Once, Optimize All Objectives: Derivative-Free Diffusion Models for Chance-Constrained Programming also fits: Diffusion and flow policies for robotics
  23. Explainable Molecular Structure Inference from GC--MS with Diffusion Models and LLM Reranking
  24. Generalization Bounds for Flow-matching Generative Models for Intrinsically Low-dimensional Data
  25. Equivariant Flow Matching for Electron Density Prediction
  26. Scale-Recursive Rectified Flows for Few-Step Precipitation Ensembles
  27. Flow Matching for Fast Posterior Sampling in Bayesian Inverse Problems
  28. Mitigating Convergence Collapse in Fixed-Target Anomaly Detectors via Kernel-Anchored Locality Regularization
  29. Graph Representation via Elements of Discrete Morse and Cobordism Theories
  30. Unsupervised Domain Adaptation for Enhanced Radiometer Image Precipitation Estimation using Conditional Flow Matching
  31. PhysDEM: Physics-Defined Energy-Matching Diffusion for Spatiotemporal Field Generation under Scarce Measurements also fits: Diffusion foundations and sampling
  32. Langevin-Informed Transfer Learning: Replacing Target Samples by Black-Box Feedback
  33. Smoother Flow Matching via Contrastive Trajectory Repulsion
  34. ProtoFlow: Prototype-Guided Flow Matching for Multivariate Time Series Forecasting
  35. Counterfactual Generation via Flow Matching: Coupling-Sensitive End-to-End Rates
  36. Rethinking Data Augmentation under Covariate Shift: Invariant-Guided Diffusion and Prototype Reweighting also fits: Diffusion foundations and sampling
  37. MintFlow: Minimal Trajectory Intervention for Constrained Flow Matching
  38. VTV-FM: Flow Matching through Variational Terminal-Velocity Closure
  39. Benchmarking Generative Models for Weather Data Assimilation on Real Station Observations
  40. Correcting CondOT: Exact Finite-Step Sampling in Gaussian Flow Matching
  41. Wavelet Flow Matching for Time Series
  42. Flow Matching under Noisy Latent Structure: Beyond Exact Low-Dimensional Support
  43. Towards Universal Wasserstein Barycenters through Flow Matching
  44. Improving Function Space Flow Matching with Kernel Optimal Transport
  45. GRFBrain: Graph-Structured Rectified Flows for EEG Dynamic Modeling
  46. Co-PiLOT: Constrained Physics-Informed Latent Optimization for Target-Driven Inverse Design
  47. GARDiff: Graph-Aligned Residual Diffusion for Probabilistic Multivariate Time-Series Forecasting
  48. Parallel Tempering for Diffusion-Based Combinatorial Optimization also fits: Diffusion foundations and sampling
  49. NowcastDiT: Diffusion Transformers are Effective Precipitation Nowcasters also fits: Diffusion foundations and sampling
  50. High-Resolution Dynamic Functional Connectivity Generation with Graph-Variate Flow Matching
  51. Variational Mixtures and Multi-Marginal Flow Matching: Advancing Statistical Inference with Biological Applications
  52. Graph-Spectral Flow Matching for Multivariate Time Series Anomaly Detection
  53. Learning Continuous Patient Trajectories from Electronic Health Records also fits: Medical imaging and segmentation
  54. Data Unlearning via Inverse Distillation also fits: Diffusion foundations and sampling
  55. EnJoi: Ensemble Joint Score Filter for Generative Data Assimilation
  56. Physics-Guided Conditional Diffusion Model for Rare Event Synthesis and Diagnosis for the Water-Gas Shift Reaction
  57. Manifold-Stable Flow Matching also fits: Diffusion and flow policies for robotics
  58. DRIFT: Disentangled Responsive-Invariant Flow Transport for Single-Cell Perturbation Prediction
  59. Probabilistic Geodesic Flow Matching on Location-Scale Families
  60. KiT: A Foundation Model for Financial Time-Series Forecasting using DiffusionTransformers
  61. GeoCFM: Positive-Only Conditional Flow Matching for Mineral Occurrence Sampling
  62. What Does a Stream Model Buy You in Flow Matching?
  63. BridgeCast: Bridging Ocean Wave Forecasts to Reanalysis via Flow Matching with Exogenous Variables
  64. Generalizable single-cell perturbation response prediction using energy-guided flow matching
  65. GeoShrink: Accelerating Diffusion Transformers with Two Lines of Code also fits: Diffusion foundations and sampling
  66. OOD Generalization as a Bifurcation Problem also fits: Diffusion and flow policies for robotics
  67. Source Anchoring for Physical Consistency in Flow Matching Models
  68. ChronoFlow: Hierarchical Flow Matching for Irregular Time Series Generation
  69. ReAL: Accelerating Flow Matching through Segment Advancement with Shared Lookahead
  70. Flow-Matching-Based Protein Structure Tokenizer Made Efficient and Easy
  71. Feasible Flow Matching for Graph Reconstruction via Within-Sampling Primal-Dual Guidance
  72. Permutation-Equivariant Flow Matching for Alignment-Free Neural Weight Generation
  73. Beyond the Manifold Hypothesis: Hybrid Spectral Parameterizations for Flow Matching
  74. A Flow Matching Framework for Neural Representational Dissimilarity
  75. CRNDiff: Count-Native Diffusion Framework via Chemical Reaction Networks also fits: Diffusion foundations and sampling
  76. Spectral Feedback for Test-Time Alignment of Protein Diffusion Models also fits: Diffusion foundations and sampling
  77. Spectral Amplitude Purification in Distribution Matching for Diffusion Distillation also fits: Diffusion foundations and sampling
  78. Memory-Conditioned Diffusion Model for Generalized Langevin Dynamics also fits: Diffusion foundations and sampling
  79. Improving Ensemble Filters with Flow Matching
  80. Active Learning for Low-Altitude Radio Map Construction via Plug-and-Play Flow Matching also fits: Diffusion for compression and wireless
  81. OMatG-flash: An All-Atom Flow Map with Reinforce Adjoint Matching for Scalable Materials Discovery
  82. Gaussian Flow-Matching Schedules: Implications for Sampling and Training
  83. When Riemann flows with Wasserstein: Generative Modeling of Probability Distributions on Manifolds
  84. Energy Time-Series Imputation with Differentially Private Diffusion Models via Clipping-Aware Objective Conditioning also fits: Diffusion foundations and sampling
  85. Mean Velocity Matching: Rethinking Generative Dynamics in Diffusion Models also fits: Diffusion foundations and sampling
  86. Classifier-Free Guidance in Flow Matching: Non-Autonomous Potentials, Overshoot, and Posterior-Mean Control also fits: Diffusion and flow policies for robotics
  87. Bayesian Filtering in Physical Systems via Test-time Trained Flow Matching
  88. When Does Adversarial Refinement Help? A Negative Result and Open Problem in Adapting R3GAN to Time Series Imputation also fits: Diffusion foundations and sampling
  89. Monotone-Constrained Diffusion Models for Long-Horizon Production Forecasting
  90. λ-Controlled GRPO: Turning Flow-Matching Ratio Instability into a Budgeted Resource also fits: Diffusion and flow policies for robotics
  91. Time series generation with spectrally aligned latent flow matching

Foundations

Most cited by papers here

  1. Flow Matching for Generative Modeling2022cited by 626 here
  2. Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow2022cited by 495 here
  3. Improving and generalizing flow-based generative models with minibatch optimal transport2023cited by 259 here
  4. Equivariant Diffusion for Molecule Generation in 3D2022cited by 199 here
  5. DiGress: Discrete Denoising diffusion for graph generation2022cited by 155 here

Lineage

The papers this direction builds on, oldest first.

Each paper on the line cites the one before.

  1. 2020Denoising Diffusion Probabilistic Modelscited by 1,176 here
  2. 2020Denoising Diffusion Implicit Modelscited by 414 here
  3. 2021Improved Denoising Diffusion Probabilistic Modelscited by 261 here
  4. 2021Diffusion Models Beat GANs on Image Synthesiscited by 496 here
  5. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 515 here
  6. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 311 here
  7. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 495 here
  8. 2023Improving and generalizing flow-based generative models with minibatch optimal transportcited by 259 here
16 more it builds on, not in this chain
  1. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesiscited by 118 here
  2. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 808 here
  3. 2021Structured Denoising Diffusion Models in Discrete State-Spacescited by 187 here
  4. 2021CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputationcited by 135 here
  5. 2022GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generationcited by 136 here
  6. 2022Equivariant Diffusion for Molecule Generation in 3Dcited by 199 here
  7. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 129 here
  8. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Stepscited by 116 here
  9. 2022Classifier-Free Diffusion Guidancecited by 287 here
  10. 2022Diffusion Posterior Sampling for General Noisy Inverse Problemscited by 118 here
  11. 2022DiGress: Discrete Denoising diffusion for graph generationcited by 155 here
  12. 2022Flow Matching for Generative Modelingcited by 626 here
  13. 2022Scalable Diffusion Models with Transformerscited by 246 here
  14. 2023Consistency Modelscited by 152 here
  15. 2023Multisample Flow Matching: Straightening Flows with Minibatch Couplingscited by 117 here
  16. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 220 here

The 24 most cited of 2,938.

Browse

30 of 1,679, ranked 6–35

  1. 6GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generation2022136
  2. 7CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputation2021135
  3. 8Multisample Flow Matching: Straightening Flows with Minibatch Couplings2023117
  4. 9Score-based Generative Modeling of Graphs via the System of Stochastic Differential Equations2022100
  5. 10Flow Matching on General Geometries202393
  6. 11Autoregressive Denoising Diffusion Models for Multivariate Probabilistic Time Series Forecasting202185
  7. 12Flow Matching Guide and Code202482
  8. 13Permutation Invariant Graph Generation via Score-Based Generative Modeling202081
  9. 14Generative Flows on Discrete State-Spaces: Enabling Multimodal Flows with Applications to Protein Co-Design202476
  10. 15Geometric Latent Diffusion Models for 3D Molecule Generation202373
All 30
  1. 16Discrete Flow Matching202471
  2. 17Structure-based Drug Design with Equivariant Diffusion Models202269
  3. 18Rectified Flow: A Marginal Preserving Approach to Optimal Transport202267
  4. 19Diffusion probabilistic modeling of protein backbones in 3D for the motif-scaffolding problem202266
  5. 20A Physics-informed Diffusion Model for High-fidelity Flow Field Reconstruction202264
  6. 21SE(3) diffusion model with application to protein backbone generation202361
  7. 22InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generation202359
  8. 23TabDDPM: Modelling Tabular Data with Diffusion Models202257
  9. 24Diffusion-TS: Interpretable Diffusion for General Time Series Generation202453
  10. 25SE(3)-Stochastic Flow Matching for Protein Backbone Generation202353
  11. 26Flow Matching in Latent Space202350
  12. 27Dirichlet Flow Matching with Applications to DNA Sequence Design202449
  13. 28Equivariant flow matching202348
  14. 29Equivariant 3D-Conditional Diffusion Models for Molecular Linker Design202248
  15. 30MiDi: Mixed Graph and 3D Denoising Diffusion for Molecule Generation202346
  16. 31DiffusionPDE: Generative PDE-Solving Under Partial Observation202445
  17. 32Improving the Training of Rectified Flows202440
  18. 33Protein structure generation via folding diffusion202239
  19. 34Diffusion Models for Graphs Benefit From Discrete State Spaces202239
  20. 35DYffusion: A Dynamics-informed Diffusion Model for Spatiotemporal Forecasting202337