This episode explores a 2026 paper, Generative Modeling via Drifting, which argues that the hard transport process behind modern generative models can be moved into training so that inference becomes a single forward pass. It explains the core idea of a pushforward distribution, introduces the paper’s notion of a drifting field that nudges generated samples toward the data distribution during optimization, and frames equilibrium as the point where those updates no longer need to move samples. The discussion compares this approach with GANs, diffusion models, flow matching, and other fast one-step systems, highlighting the tradeoff between low-latency generation and the quality advantages of multi-step correction. A listener would find it interesting because it lays out a possible new generative modeling paradigm and tests whether one-shot generation can become more than just an accelerated approximation of diffusion.

Sources:

1. Generative Modeling via Drifting — Mingyang Deng, He Li, Tianhong Li, Yilun Du, Kaiming He, 2026

http://arxiv.org/abs/2602.04770

2. Generative Adversarial Nets — Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, Yoshua Bengio, 2014

https://neurips.cc/virtual/2014/poster/4618

3. Generative Moment Matching Networks — Yujia Li, Kevin Swersky, Rich Zemel, 2015

https://proceedings.mlr.press/v37/li15.html

4. Consistency Models — Yang Song, Prafulla Dhariwal, Mark Chen, Ilya Sutskever, 2023

https://icml.cc/virtual/2023/poster/24593

5. Adversarial Diffusion Distillation — Stability AI researchers, 2023

https://stability.ai/research/adversarial-diffusion-distillation

6. A Kernel Two-Sample Test — Arthur Gretton, Karsten M. Borgwardt, Malte J. Rasch, Bernhard Scholkopf, Alexander Smola, 2012

https://www.jmlr.org/beta/papers/v13/gretton12a.html

7. Wasserstein GAN — Martin Arjovsky, Soumith Chintala, Leon Bottou, 2017

https://icml.cc/virtual/2017/poster/799

8. Density Estimation using Real NVP — Laurent Dinh, Jascha Sohl-Dickstein, Samy Bengio, 2017

https://openreview.net/forum?id=HkpbnH9lx

9. Glow: Generative Flow with Invertible 1x1 Convolutions — Diederik P. Kingma, Prafulla Dhariwal, 2018

https://openai.com/index/glow/

10. Flow Matching for Generative Modeling — Yaron Lipman, Ricky T. Q. Chen, Heli Ben-Hamu, Maximilian Nickel, Matt Le, 2023

https://openreview.net/forum?id=PqvMRDCJT9t

11. Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow — Xingchao Liu, Chengyue Gong, Qiang Liu, 2022

https://openreview.net/forum?id=gWxpdtQpiYV

12. Large Scale GAN Training for High Fidelity Natural Image Synthesis — Andrew Brock, Jeff Donahue, Karen Simonyan, 2018

https://huggingface.co/papers/1809.11096

13. Diffusion Models Beat GANs on Image Synthesis — Prafulla Dhariwal, Alex Nichol, 2021

https://openreview.net/forum?id=AAWuCvzaVt

14. High-Resolution Image Synthesis with Latent Diffusion Models — Robin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser, Bjorn Ommer, 2022

https://openaccess.thecvf.com/content/CVPR2022/html/Rombach_High-Resolution_Image_Synthesis_With_Latent_Diffusion_Models_CVPR_2022_paper.html

15. Scalable Diffusion Models with Transformers — William Peebles, Saining Xie, 2023

https://openaccess.thecvf.com/content/ICCV2023/html/Peebles_Scalable_Diffusion_Models_with_Transformers_ICCV_2023_paper.html

16. Denoising Diffusion Probabilistic Models — Jonathan Ho, Ajay Jain, Pieter Abbeel, 2020

https://scholar.google.com/scholar?q=Denoising+Diffusion+Probabilistic+Models

17. Progressive Distillation for Fast Sampling of Diffusion Models — Tim Salimans, Jonathan Ho, 2022

https://scholar.google.com/scholar?q=Progressive+Distillation+for+Fast+Sampling+of+Diffusion+Models

18. Unsupervised Image-to-Image Translation Networks — Ferenc Huszar and coauthors are not cited here; instead the more relevant cited moment-matching line is:, 2015

https://scholar.google.com/scholar?q=Unsupervised+Image-to-Image+Translation+Networks

19. Auto-Encoding Variational Bayes — Diederik P. Kingma, Max Welling, 2013

https://scholar.google.com/scholar?q=Auto-Encoding+Variational+Bayes

20. One-step diffusion with distribution matching distillation — approx. diffusion-distillation literature, recent

https://scholar.google.com/scholar?q=One-step+diffusion+with+distribution+matching+distillation

21. One-step diffusion distillation via deep equilibrium models — approx. diffusion-distillation / equilibrium-model authors, recent

https://scholar.google.com/scholar?q=One-step+diffusion+distillation+via+deep+equilibrium+models

22. Discrete Flow Matching — approx. flow-matching authors, recent

https://scholar.google.com/scholar?q=Discrete+Flow+Matching

23. Elucidating the design choice of probability paths in flow matching for forecasting — approx. forecasting / flow-matching authors, recent

https://scholar.google.com/scholar?q=Elucidating+the+design+choice+of+probability+paths+in+flow+matching+for+forecasting

24. Mixed Autoregressive and Diffusion Transformers for Continuous Image Generation — approx. hybrid AR-diffusion authors, recent

https://scholar.google.com/scholar?q=Mixed+Autoregressive+and+Diffusion+Transformers+for+Continuous+Image+Generation

25. ACDiT: Interpolating autoregressive conditional modeling and diffusion transformer — approx. ACDiT authors, 2025

https://scholar.google.com/scholar?q=ACDiT%3A+Interpolating+autoregressive+conditional+modeling+and+diffusion+transformer

26. AI Post Transformers: Paris: Decentralized Open-Weight Diffusion Model — Hal Turing & Dr. Ada Shannon, 2025

https://podcast.do-not-panic.com/episodes/paris-decentralized-open-weight-diffusion-model/

Interactive Visualization: Generative Modeling via Drifting in One Step