Metraipolis › archive › dc_04eb0345bc49

Revisiting Spectral Representations in Generative Diffusion Models — arXiv:2609.08253

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.08253
License (as archived): CC0-1.0
Archived: 2026-10-16T13:58:10.848Z
SHA-256 of the archived text: 9d5c652aef0e167a41a4040dcf03f93de2fe62db914f4da2b749073456e84979
Stable URL of this page: https://metraipolis.com/documento/dc_04eb0345bc49

How to cite

Revisiting Spectral Representations in Generative Diffusion Models — arXiv:2609.08253 — arXiv (en), https://arxiv.org/abs/2609.08253 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_04eb0345bc49 (Metraipolis archive dc_04eb0345bc49, sha256 9d5c652aef0e167a41a4040dcf03f93de2fe62db914f4da2b749073456e84979)

BibTeX

@misc{dc04eb0345bc49,
  title = {Revisiting Spectral Representations in Generative Diffusion Models — arXiv:2609.08253},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.08253},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_04eb0345bc49; sha256 9d5c652aef0e167a41a4040dcf03f93de2fe62db914f4da2b749073456e84979},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.08253. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Diffusion models have shown remarkable performance on diverse generation tasks. Recent work finds that imposing representation alignment on the hidden states of diffusion networks can both facilitate training convergence and enhance sampling quality, yet the mechanism driving this synergy remains insufficiently understood. In this paper, we investigate the connection between self-supervised spectral representation learning and diffusion generative models through a shared perspective on perturbation kernels. On the diffusion side, samples (e.g., images, videos) are produced by reversing a stochastic noise-injection process specified by Gaussian kernels; on the spectral representation side, spectral embeddings emerge from contrasting positive and negative relations induced by random perturbation kernels. Motivated by this, we propose a self-supervised spectral representation alignment method to facilitate diffusion model training. In addition, we clarify how joint spectral learning can benefit diffusion training from a geometric perspective. Furthermore, we find that the optimization of the spectral alignment objective is in an equivalent form of diffusion score distillation in the representation space. Building on these findings, we integrate a spectral regularizer into diffusion training objectives to improve the performance of diffusion models on multiple datasets. Experiments across images and 3D point clouds show consistent gains in generation quality. Code is released at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-09 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.08253 — 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 2026-10-16T13:39:43.029Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).