Metraipolis › archive › dc_2a2f56366a0d

A Plug-in Interpretation of Conditioning in Score-Based Diffusion Models — arXiv:2608.19504

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.19504
License (as archived)
CC0-1.0
Archived
2026-10-18T12:04:34.076Z
SHA-256 of the archived text
8eaa365142cb3e8277500a05934cff28eb3d9e9cad2edd0a29530a0cd8f175b0
Stable URL of this page
https://metraipolis.com/documento/dc_2a2f56366a0d

How to cite

A Plug-in Interpretation of Conditioning in Score-Based Diffusion Models — arXiv:2608.19504 — arXiv (en), https://arxiv.org/abs/2608.19504 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2a2f56366a0d (Metraipolis archive dc_2a2f56366a0d, sha256 8eaa365142cb3e8277500a05934cff28eb3d9e9cad2edd0a29530a0cd8f175b0)
BibTeX
@misc{dc2a2f56366a0d,
  title = {A Plug-in Interpretation of Conditioning in Score-Based Diffusion Models — arXiv:2608.19504},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.19504},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2a2f56366a0d; sha256 8eaa365142cb3e8277500a05934cff28eb3d9e9cad2edd0a29530a0cd8f175b0},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.19504. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We propose a conditioning mechanism for diffusion models based on multi-speed joint diffusion of the target and the condition. The mechanism learns an unconditional joint score network and enforces conditioning at inference via a plug-in correction term. The plug-in term separates the conditioning contribution from the learned unconditional dynamics, offering a transparent view of how the condition steers generation of the target distribution. Building on this, we derive explicit conditional reverse-time SDEs and approximate probability-flow ODEs, enabling principled and directly comparable conditional samplers. To reduce the induced ODE--SDE discrepancy, we introduce a log-Fokker--Planck residual regularization that improves ODE sampling quality. Experiments on conditional image generation tasks demonstrate competitive performance and support the effectiveness of the plug-in conditioning view. Additional ODE--SDE comparison experiments show that the log-Fokker--Planck residual regularization improves deterministic ODE sampling.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-21 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.19504 — 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 2026-10-18T12:01:57.692Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).