EUVIMEDEUVIMED entdecken
Crossref

$$\Delta $$-DiT: Accelerating Diffusion Transformers without Training via Denoising Property Alignment

Pengtao Chen, Mingzhu Shen, Peng Ye, Jianjian Cao, Chongjun Tu, Christos-Savvas Bouganis, Yiren Zhao, Tao Chen

International Journal of Computer Vision · 2026-06 · 134 (6)

DOI: 10.1007/s11263-026-02871-7 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Computer Vision, online erschienen am 19.05.2026. Verfasst von Pengtao Chen und 7 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 67 Literaturangaben. Gefördert von: National Key Research and Development Program of China, Shanghai Natural Science Foundation, Shanghai Science and Technology Commission Explorer Program Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Kein Abstract verfügbar.

Förderung

  • National Key Research and Development Program of China
  • Shanghai Natural Science Foundation
  • Shanghai Science and Technology Commission Explorer Program Project
  • Shanghai Municipal Science and Technology Major Project

Zitieren

APA

Chen, P., Shen, M., Ye, P., Cao, J., Tu, C., Bouganis, C., Zhao, Y., & Chen, T. (2026). $$\Delta $$-DiT: Accelerating Diffusion Transformers without Training via Denoising Property Alignment. International Journal of Computer Vision, 134(6). https://doi.org/10.1007/s11263-026-02871-7

Vancouver

Chen P, Shen M, Ye P, Cao J, Tu C, Bouganis C, et al. $$\Delta $$-DiT: Accelerating Diffusion Transformers without Training via Denoising Property Alignment. International Journal of Computer Vision. 2026;134(6). doi:10.1007/s11263-026-02871-7

BibTeX
@article{Chen2026,
  author = {Chen, Pengtao and Shen, Mingzhu and Ye, Peng and Cao, Jianjian and Tu, Chongjun and Bouganis, Christos-Savvas and Zhao, Yiren and Chen, Tao},
  title = {$$\Delta $$-DiT: Accelerating Diffusion Transformers without Training via Denoising Property Alignment},
  journal = {International Journal of Computer Vision},
  year = {2026},
  volume = {134},
  number = {6},
  doi = {10.1007/s11263-026-02871-7}
}
Kostenlos starten →