Metraipolis › archive › dc_95adb0402834
RouteREPA: Routed Representation Alignment for Just Image Transformers — arXiv:2611.02941
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.02941
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T11:26:45.397Z
- SHA-256 of the archived text
ccb237855d50e7d81fdcc2844dbc8603a9e8eb595f5dd6572ecb60d05ed6f31e- Stable URL of this page
https://metraipolis.com/documento/dc_95adb0402834
How to cite
RouteREPA: Routed Representation Alignment for Just Image Transformers — arXiv:2611.02941 — arXiv (en), https://arxiv.org/abs/2611.02941 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_95adb0402834 (Metraipolis archive dc_95adb0402834, sha256 ccb237855d50e7d81fdcc2844dbc8603a9e8eb595f5dd6572ecb60d05ed6f31e)
BibTeX
@misc{dc95adb0402834,
title = {RouteREPA: Routed Representation Alignment for Just Image Transformers — arXiv:2611.02941},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.02941},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_95adb0402834; sha256 ccb237855d50e7d81fdcc2844dbc8603a9e8eb595f5dd6572ecb60d05ed6f31e},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.02941. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Representation alignment (REPA) is widely used to accelerate the training of latent-space diffusion transformers (DiTs). However, applying it to pixel-space models such as Just Image Transformers (JiT) is challenging. Our analysis reveals a pronounced representation conflict between discriminative alignment and pixel-space generation. Compared with its latent counterpart, JiT learns representations that are substantially less aligned with DINOv2. Applying REPA to JiT consistently reduces the reconstructability of its intermediate representations, whereas this effect is not observed in Latent JiT. We attribute this conflict to JiT directly reconstructing pixels, which requires its representations to hierarchically encode discriminative semantics and reconstruction-relevant visual information across network depths. To address these challenges, we propose Routed Representation Alignment (RouteREPA), which uses lightweight, representation-dependent routers to adaptively route task-oriented representations for alignment and generation. We further apply routing across multiple network depths to accommodate their depth-dependent representation requirements. Extensive experiments on ImageNet-1K at 256x256 resolution show that RouteREPA consistently improves JiT across model scales and training budgets, outperforming standard REPA. On JiT-H/16, RouteREPA further surpasses PixelREPA using only one-third of its training epochs without classifier-free guidance. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2611.02941 — 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 2026-11-03T11:02:37.892Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).