Metraipolis › archive › dc_1179ad2fb609
ToDoPro: Faster and Better Reference-Based Generation: Early Token Reduction via Downsampled Self-Probing — arXiv:2610.34782
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.34782
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-27T08:02:09.016Z
- SHA-256 of the archived text
6509b4af958c252452b3a53ae8f33a7cbf654a2486a5306007984b5a290f2634- Stable URL of this page
https://metraipolis.com/documento/dc_1179ad2fb609
How to cite
ToDoPro: Faster and Better Reference-Based Generation: Early Token Reduction via Downsampled Self-Probing — arXiv:2610.34782 — arXiv (en), https://arxiv.org/abs/2610.34782 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_1179ad2fb609 (Metraipolis archive dc_1179ad2fb609, sha256 6509b4af958c252452b3a53ae8f33a7cbf654a2486a5306007984b5a290f2634)
BibTeX
@misc{dc1179ad2fb609,
title = {ToDoPro: Faster and Better Reference-Based Generation: Early Token Reduction via Downsampled Self-Probing — arXiv:2610.34782},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.34782},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_1179ad2fb609; sha256 6509b4af958c252452b3a53ae8f33a7cbf654a2486a5306007984b5a290f2634},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.34782. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Recent generic reference-based image generation models natively support multiple conditions by concatenating all reference image and text tokens into a joint sequence processed by a single Diffusion Transformer (DiT). However, this versatile paradigm comes at an efficiency cost: accommodating multiple references leads to a token explosion, incurring massive $\mathcal{O}(N^2)$ computational complexity. Most acceleration methods operate inside the DiT, showing limited capability in reducing spatial redundancy and failing to alleviate peak VRAM. While some pre-model token reduction alternatives exist, they inevitably introduce external models. This raises a question: Is it possible to achieve acceleration and memory savings while preserving compatibility with in-model techniques and requiring no additional parameters? In this work, we realize this goal by proposing the early Token reduction via Downsampled self-Probing (ToDoPro). By executing a few denoising steps on spatially $2\times$ downsampled reference images, this cheap probing stage utilizes the DiT model itself to effectively and efficiently extract reference token importance. Using the probed importance, we apply a hierarchical reduction before the main denoising stage: we completely discard low-importance tokens, substitute mid-importance tokens with their downsampled counterparts to cheaply preserve global context, and keep high-importance tokens. Experiments across three base models and two benchmarks demonstrate that our early reduction accelerates inference significantly and mitigates peak GPU memory. Furthermore, we can improve generation quality by safely filtering out noisy, uninformative reference tokens, enabling the model to concentrate its limited attention capacity on genuinely useful tokens. The code will be released at this https URL
Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.34782 — 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 2026-10-27T07:55:30.939Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).