Metraipolis › archive › dc_09a2bd2672f7
One-Step Generation via Riemannian Wasserstein Gradient Flows — arXiv:2610.04454
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.04454
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T05:30:35.229Z
- SHA-256 of the archived text
22dfdf17f654b014cfb4c12adb28881c28eddf3f1772dc91066393d9117ee58b- Stable URL of this page
https://metraipolis.com/documento/dc_09a2bd2672f7
How to cite
One-Step Generation via Riemannian Wasserstein Gradient Flows — arXiv:2610.04454 — arXiv, https://arxiv.org/abs/2610.04454 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_09a2bd2672f7 (Metraipolis archive dc_09a2bd2672f7, sha256 22dfdf17f654b014cfb4c12adb28881c28eddf3f1772dc91066393d9117ee58b)
BibTeX
@misc{dc09a2bd2672f7,
title = {One-Step Generation via Riemannian Wasserstein Gradient Flows — arXiv:2610.04454},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.04454},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_09a2bd2672f7; sha256 22dfdf17f654b014cfb4c12adb28881c28eddf3f1772dc91066393d9117ee58b},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.04454. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Recently, Drifting Models and Wasserstein Gradient Flows have attracted substantial attention because they move iterative distributional refinement to training and amortize it into a generator, enabling fast inference. However, existing formulations have been developed largely for continuous Euclidean domains, such as image spaces, where particles admit unconstrained additive updates. On constrained spaces, these updates can leave the valid domain or ignore its geometry, making them unsuitable targets for training. Recent work has adapted updates to these spaces, but has focused on particular fields or offered limited empirical comparison. We derive and compare several geometry-aware fields within a common training framework for one-step generators. We test the method on data with different structures and obtain competitive one-step results in each setting. The best-performing field varies by task, showing why the choice of objective matters in practice. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2610.04454 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-06T05:27:05.684Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).