Metraipolis › archive › dc_c028c0fd4c0e

SALD: Self-Referenced Advantage Learning for Diffusion Models — arXiv:2610.01496

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.01496
License (as archived)
CC0-1.0
Archived
2026-10-06T19:13:39.141Z
SHA-256 of the archived text
c176ea53925ef7dbbbca5bf46e6dcdb73dca964d7617214f425aef50c1deae1a
Stable URL of this page
https://metraipolis.com/documento/dc_c028c0fd4c0e

How to cite

SALD: Self-Referenced Advantage Learning for Diffusion Models — arXiv:2610.01496 — arXiv (en), https://arxiv.org/abs/2610.01496 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c028c0fd4c0e (Metraipolis archive dc_c028c0fd4c0e, sha256 c176ea53925ef7dbbbca5bf46e6dcdb73dca964d7617214f425aef50c1deae1a)
BibTeX
@misc{dcc028c0fd4c0e,
  title = {SALD: Self-Referenced Advantage Learning for Diffusion Models — arXiv:2610.01496},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.01496},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c028c0fd4c0e; sha256 c176ea53925ef7dbbbca5bf46e6dcdb73dca964d7617214f425aef50c1deae1a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.01496. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Recent work on language-model adaptation has shown that single models can obtain informative training signals by evaluating their behavior in demonstrationor feedback-augmented contexts, with the help of a teacher network, which is driven by the student's learned parameters. Inspired by this internal-reference principle, we investigate how diffusion models can identify self-referenced training signals without external demonstrations or teacher networks. We introduce SALD, a self-referenced training framework that evaluates each image-caption pair at two noise levels using the same model. The easier, lower-noise path is evaluated without gradient tracking to provide a reference, while the harder, higher-noise path provides the training gradient. Rather than directly distilling the easy-path prediction, SALD uses the difference between two path errors to adapt the hardpath objective. The proposed Advantage-Guided Diffusion (AGD) converts this relative error into a differentiable sample-level weight. Temporal Advantage Memory (TAM) accumulates relative difficulty across training and adapts the future gap between the two noise levels. Spectral Advantage Decomposition (SAD) further compares the residual power spectra of the two paths and constructs a differentiable, frequency-derived latent-element weight. All components share a single set of model parameters, requiring neither an external teacher network nor additional trainable parameters during training or inference, and no modification to the inference procedure. Experiments across multiple architectures and datasets demonstrate consistent improvements in generation quality, while component-wise ablations quantify the contributions of the proposed components.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-10-02 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.01496 — 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 2026-10-06T17:37:36.793Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).