mlsanityData to 13 Oct 2026

FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Models

arXiv 1810.01367 ↗First posted 2 Oct 2018cs.LG cs.CV stat.MLcited by 588

Not on the map. Why?

Cited by 174 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

A promising class of generative models maps points from a simple distribution to a complex distribution through an invertible neural network. Likelihood-based training of these models requires restricting their architectures to allow cheap computation of Jacobian determinants. Alternatively, the Jacobian trace can be used if the transformation is specified by an ordinary differential equation. In this paper, we use Hutchinson's trace estimator to give a scalable unbiased estimate of the log-density. The result is a continuous-time invertible generative model with unbiased density estimation and one-pass sampling, while allowing unrestricted neural network architectures. We demonstrate our approach on high-dimensional density estimation, image generation, and variational inference, achieving the state-of-the-art among exact likelihood methods with efficient sampling.

Key facts. Cited by 588 papers in the map (data through 13 Oct 2026). First posted on arXiv 2 Oct 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2020: 1; 2021: 100; 2022: 93; 2023: 104; 2024: 77; 2025: 110; 2026: 103.

588 papers.

Sort:

By area:

  1. 2020Denoising Diffusion Implicit Modelscited by 9,718
  2. 2022Flow Matching for Generative Modelingcited by 5,542
  3. 2023Improving and generalizing flow-based generative models with minibatch optimal transportcited by 857
  4. 2021Diffusion Probabilistic Models for 3D Point Cloud Generationcited by 734
  5. 2021Maximum Likelihood Training of Score-Based Diffusion Modelscited by 671
  6. 2021Score-based Generative Modeling in Latent Spacecited by 635
  7. 2022LION: Latent Point Diffusion Models for 3D Shape Generationcited by 553
  8. 2023Flow Matching on General Geometriescited by 262
  9. 2021Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Modelscited by 252
  10. 2021Score-Based Generative Modeling with Critically-Damped Langevin Diffusioncited by 231
  11. 2021Likelihood Training of Schr"odinger Bridge using Forward-Backward SDEs Theorycited by 218
  12. 2023MotionDiffuser: Controllable Multi-Agent Motion Prediction using Diffusioncited by 212
38 more
  1. 2021A Variational Perspective on Diffusion-Based Generative Models and Score Matchingcited by 182
  2. 2021Path Integral Sampler: a stochastic control approach for samplingcited by 178
  3. 2021E(n) Equivariant Normalizing Flowscited by 165
  4. 2021Neural SDEs as Infinite-Dimensional GANscited by 161
  5. 2023Flow Matching in Latent Spacecited by 157
  6. 2022Concrete Score Matching: Generalized Score Matching for Discrete Datacited by 146
  7. 2023Denoising Diffusion Samplerscited by 146
  8. 2022GENIE: Higher-Order Denoising Diffusion Solverscited by 127
  9. 2023Score-Based Diffusion Models as Principled Priors for Inverse Imagingcited by 127
  10. 2022gDDIM: Generalized denoising diffusion implicit modelscited by 125
  11. 2024D-Flow: Differentiating through Flows for Controlled Generationcited by 120
  12. 2021Natural Synthetic Anomalies for Self-Supervised Anomaly Detection and Localizationcited by 116
  13. 2022Generative Flow Networks for Discrete Probabilistic Modelingcited by 113
  14. 2023Diffusion Models for Image Restoration and Enhancement: A Comprehensive Surveycited by 109
  15. 2024Flow map matching with stochastic interpolants: A mathematical framework for consistency modelscited by 107
  16. 2021An Introduction to Deep Generative Modelingcited by 104
  17. 2022DiffuseVAE: Efficient, Controllable and High-Fidelity Generation from Low-Dimensional Latentscited by 103
  18. 2021Neural Flows: Efficient Alternative to Neural ODEscited by 100
  19. 2023On the Stability of Iterative Retraining of Generative Models on their own Datacited by 98
  20. 2022Poisson Flow Generative Modelscited by 95
  21. 2021Proximal Optimal Transport Modeling of Population Dynamicscited by 93
  22. 2023Error Bounds for Flow Matching Methodscited by 90
  23. 2024Normalizing Flows are Capable Generative Modelscited by 89
  24. 2021Learning Neural Generative Dynamics for Molecular Conformation Generationcited by 88
  25. 2022STaSy: Score-based Tabular data Synthesiscited by 85
  26. 2023Simulation-free Schr"odinger bridges via score and flow matchingcited by 81
  27. 2022Maximum Likelihood Training for Score-Based Diffusion ODEs by High-Order Denoising Score Matchingcited by 80
  28. 2021Diffusion Normalizing Flowcited by 77
  29. 2023Training-free Linear Image Inverses via Flowscited by 72
  30. 2021Stabilizing Equilibrium Models by Jacobian Regularizationcited by 71
  31. 2021Unleashing Transformers: Parallel Token Prediction with Discrete Absorbing Diffusion for Fast High-Resolution Image Generation from Vector-Quantized Codescited by 71
  32. 2021Moser Flow: Divergence-based Generative Modeling on Manifoldscited by 67
  33. 2022Progressive Distillation for Fast Sampling of Diffusion Modelscited by 67
  34. 2021Closed-form Continuous-time Neural Modelscited by 65
  35. 2022Manifold Interpolating Optimal-Transport Flows for Trajectory Inferencecited by 63
  36. 2021Density Ratio Estimation via Infinitesimal Classificationcited by 61
  37. 2022Towards Blind Watermarking: Combining Invertible and Non-invertible Mechanismscited by 61
  38. 2021SemanticStyleGAN: Learning Compositional Generative Priors for Controllable Image Synthesis and Editingcited by 58

50 most cited of 588 All 588 (JSON)