Metraipolis › archive › dc_9b6030aff40b

Multi-Bandwidth Distribution Matching Distillation: On the Equivalence of Distribution Matching Distillation and Drifting Models — arXiv:2610.10989

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.10989
License (as archived)
CC0-1.0
Archived
2026-10-09T06:21:10.529Z
SHA-256 of the archived text
90d4529b3d001d452a95beee5e04d770c18f73ab1b5ddb683df7b2d7b89dd31a
Stable URL of this page
https://metraipolis.com/documento/dc_9b6030aff40b

How to cite

Multi-Bandwidth Distribution Matching Distillation: On the Equivalence of Distribution Matching Distillation and Drifting Models — arXiv:2610.10989 — arXiv (en), https://arxiv.org/abs/2610.10989 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9b6030aff40b (Metraipolis archive dc_9b6030aff40b, sha256 90d4529b3d001d452a95beee5e04d770c18f73ab1b5ddb683df7b2d7b89dd31a)
BibTeX
@misc{dc9b6030aff40b,
  title = {Multi-Bandwidth Distribution Matching Distillation: On the Equivalence of Distribution Matching Distillation and Drifting Models — arXiv:2610.10989},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.10989},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9b6030aff40b; sha256 90d4529b3d001d452a95beee5e04d770c18f73ab1b5ddb683df7b2d7b89dd31a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.10989. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Researchers are exploring effective one-step generative model continuously, and, Drifting Models (Deng et al., 2026), demonstrate great potential in one-step generation recently. There are works that reveal the connection between Diffusion & Flow Style Generative Models (DFSGMs) (Ho et al., 2020; Song et al., 2020a;b; Lipman et al., 2022; Liu et al., 2022) and Drifting Models (Li & Zhu, 2026; Lai et al., 2026; Turan et al., 2026). But no one has yet established a precise correspondence between the Drifting Model and the widely used distillation method- Distribution Matching Distillation (DMD/DMD2) (Yin et al., 2024b;a) to the best of our knowledge, even though their optimization objective formulas are virtually identical. In this paper, we prove that by converting the velocity-field / noise-field from the pre-trained DFSGMs into the attraction force field in Drifting Models and estimating the repulsion force field from the generative distribution, training the Drifting Model is naturally equivalent to the Distribution Matching Distillation. With this equivalent concept, we propose an improved method based on DMD from the Drifting Model's perspective- Multi-Bandwidth Distribution Matching Distillation (MBDMD).

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.10989 — 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 2026-10-09T05:50:31.090Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).