Metraipolis › archive › dc_0efa5745f2c8
Logit Refiner: Improving Visual Autoregressive Models via Intra-Scale Dependency Modeling — arXiv:2609.11804
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.11804
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T05:27:13.655Z
- SHA-256 of the archived text
64f0845ce33fc77d741903c866d80b7d190982f4ceba71740b82f89f6bd0f13f- Stable URL of this page
https://metraipolis.com/documento/dc_0efa5745f2c8
How to cite
Logit Refiner: Improving Visual Autoregressive Models via Intra-Scale Dependency Modeling — arXiv:2609.11804 — arXiv (en), https://arxiv.org/abs/2609.11804 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0efa5745f2c8 (Metraipolis archive dc_0efa5745f2c8, sha256 64f0845ce33fc77d741903c866d80b7d190982f4ceba71740b82f89f6bd0f13f)
BibTeX
@misc{dc0efa5745f2c8,
title = {Logit Refiner: Improving Visual Autoregressive Models via Intra-Scale Dependency Modeling — arXiv:2609.11804},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.11804},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0efa5745f2c8; sha256 64f0845ce33fc77d741903c866d80b7d190982f4ceba71740b82f89f6bd0f13f},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.11804. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Visual Autoregressive Models (VAR) generate images through next-scale prediction, producing all tokens within each scale in parallel. We show that this parallel decoding constitutes a mean-field-style approximation that discards spatial dependencies among same-scale tokens, causing locally incoherent samples regardless of backbone capacity -- a limitation of the decoding rule. Addressing this limitation, we introduce the Logit Refiner, a lightweight autoregressive module that restores intra-scale dependencies by sequentially sampling tokens conditioned on frozen backbone features. Adding only ~10% parameters and less than 5% of the base model's training compute, it plugs into any pretrained VAR checkpoint without retraining. Controlled ablations isolate joint intra-scale sampling -- rather than additional capacity or training -- as the critical ingredient. Across backbones from 310M to 2B parameters on class-conditional ImageNet 256x256, the refiner consistently improves generation quality, enabling a 1.1B-parameter model to surpass one twice its size. The approach further generalizes to text-to-image generation, confirming that the mean-field bottleneck persists across VAR variants and is effectively alleviated by our method. Project page: this https URL Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-11 in cs.AI). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.11804 — 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 2026-10-16T05:17:52.200Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).