arXiv Machine Learning By Arkadii Kazanskii, Tatiana Petrova, Andrey Ustyuzhanin, Konstantin Bagrianskii, Aleksandr Puzikov, Radu State

Friction-Augmented Drifting Models for Resource-Efficient Domain Translation

Read the original on arXiv Machine Learning →

arXiv:2604. 18194v2 Announce Type: replace Abstract: Single-step generators promise high-fidelity synthesis at a fraction of the inference and training cost of ordinary differential equation (ODE)-based flow models, a central concern when compute is limited.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

Hugging Face Trending Papers
Jul 20

AGG: Jacobian-Aggregated Group Gradient for Efficient GRPO Training of Diffusion Models

Group Relative Policy Optimization (GRPO) is a powerful reinforcement learning algorithm for aligning generative models with human preferences. While successful in large language models~\cite{shao2024deepseekmathpushinglimitsmathematical}, its extension to diffusion and flow matching models introduces a severe computational bottleneck: gradients must be back-propagated through the high-capacity DiT backbone at \emph{every} timestep of the sampling trajectory, making high-resolution text-to-image (T2I) training prohibitively expensive.

arXiv Machine Learning
Jul 14

Velocity Scheduled Flow Matching

arXiv:2607. 11442v1 Announce Type: new Abstract: Flow matching trains a neural network to regress the conditional velocity along a linear interpolant between noise and data, and the number of network evaluations~(NFE) sets the cost of sampling.

By Vitalii Bondar