arXiv · 2610.00518
One-Step Generative Modeling via Training Dynamics Action
Abstract
Recent one-step generators learn to move outputs toward data by fitting sample movements. However, the optimizer updates shared parameters rather than sample positions, so the movements can differ from those prescribed. To address this issue, we propose Training Dynamics Action (TDAC), which uses the cost of fitting movements jointly to choose transport plans. For a linearized generator, local generator action is the minimum sum of parameter-update cost and a feature-fitting penalty over shared parameter increments. We derive a closed-form action and minimize a regularized version while retaining a prescribed fraction of the reference plan's predicted distributional improvement. We estimate the covariance of feature responses using random parameter directions and evaluate action with a low-rank approximation. The plan defines fixed regression targets. An execution-gap bound relates local generator action to first-order progress of the actual update. Planning occurs during training; inference requires one generator evaluation. On ImageNet 256 x 256, TDAC achieves Frechet Inception Distance (FID) below 1.1 without distillation. Furthermore, TDAC reduces optimizer-time action while maintaining distributional accuracy and full mode coverage. At comparable FID, TDAC requires approximately 100 times fewer generator evaluations than multi-step diffusion models. The code for our work will be released soon.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Zhangyong Liang, Ying Huang, Haibin Ling. 2026-11-16. One-Step Generative Modeling via Training Dynamics Action. https://searcharxiv.com/abs/2610.00518
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.