Hugging Face Trending Papers

ROMS-IMLE: A Minimalist Approach to Competitive Single-Step Generative Modelling

Read the original on Hugging Face Trending Papers →

Generative models have undergone many generations of evolution, from VAEs/GANs to diffusion/flow matching. Along the way, the underlying techniques have become more complicated and various beliefs about what drives strong empirical performance have taken hold.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

arXiv Machine Learning
Jun 9

Midpoint Generative Models

arXiv:2605. 29920v2 Announce Type: replace Abstract: We introduce Midpoint Generative Models (MGM), a principled framework for training one-step generative models.

By Daniil Shlenskii, Nikita Gushchin, Lev Novitskiy, Dmitry V. Dylov, Alexander Korotin
arXiv AI
Jun 2

Heterogeneous Decentralized Diffusion Models

arXiv:2603. 06741v2 Announce Type: replace-cross Abstract: Training frontier-scale diffusion models often requires substantial computational resources concentrated in tightly-coupled clusters, limiting participation to well-resourced institutions.

By Zhiying Jiang, Raihan Seraj, Marcos Villagra, Bidhan Roy