Metraipolis › archive › dc_9bfa030170fe

Context-Aware Autoregressive Image Generation for Emerging Reasoning Properties — arXiv:2611.06838

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.06838
License (as archived)
CC0-1.0
Archived
2026-11-05T18:30:13.255Z
SHA-256 of the archived text
bebec19b1a0363628ee117b89a678e81d7303532e109a426f8aa6af51a8832e7
Stable URL of this page
https://metraipolis.com/documento/dc_9bfa030170fe

How to cite

Context-Aware Autoregressive Image Generation for Emerging Reasoning Properties — arXiv:2611.06838 — arXiv (en), https://arxiv.org/abs/2611.06838 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9bfa030170fe (Metraipolis archive dc_9bfa030170fe, sha256 bebec19b1a0363628ee117b89a678e81d7303532e109a426f8aa6af51a8832e7)
BibTeX
@misc{dc9bfa030170fe,
  title = {Context-Aware Autoregressive Image Generation for Emerging Reasoning Properties — arXiv:2611.06838},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.06838},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9bfa030170fe; sha256 bebec19b1a0363628ee117b89a678e81d7303532e109a426f8aa6af51a8832e7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.06838. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Autoregressive image generation has recently emerged as a competitive visual generation paradigm, yet its generation order is often predefined or heuristic, such as next-patch prediction, random-order prediction, or one-step generation for specific scales. We observe that these strategies can cause models to overlook important structural dependencies in images, thereby limiting both structural robustness and reasoning capability. In this work, we propose a context-aware autoregressive generation framework, where the model dynamically determines the next token location based on global context and current local information. Rather than following a fixed or random order, our method allows the generation process to adapt to image structure and semantic dependencies. Extensive experiments show that context-aware generation significantly improves structural robustness across different image AR paradigms, including masked autoregressive and scale-wise autoregressive models. Beyond quantitative improvements, we further observe emerging reasoning properties: the model can better understand complex semantic instructions and generate images that more faithfully follow the given guidance. These findings suggest that generation order is a critical yet underexplored factor in image autoregressive modeling, and that context-aware decoding can unlock stronger reasoning-aware visual generation capabilities. Code is available at this https URL .

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2611.06838 — 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 2026-11-05T18:19:49.065Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).