@inproceedings{wang-etal-2025-visual,
    title = "Visual Self-Refinement for Autoregressive Models",
    author = "Wang, Jiamian  and
      Zhou, Ziqi  and
      Mummadi, Chaithanya Kumar  and
      Dianat, Sohail  and
      Rabbani, Majid  and
      Rao, Raghuveer  and
      Qiu, Chen  and
      Tao, Zhiqiang",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.findings-emnlp.1161/",
    doi = "10.18653/v1/2025.findings-emnlp.1161",
    pages = "21291--21300",
    ISBN = "979-8-89176-335-7",
    abstract = "Autoregressive models excel in sequential modeling and have proven to be effective for vision-language data. However, the spatial nature of visual signals conflicts with the sequential dependencies of next-token prediction, leading to suboptimal results. This work proposes a plug-and-play refinement module to enhance the complex spatial correspondence modeling within the generated visual sequence. This module operates as a post-pretraining step tojointly refine all generated tokens of autoregressive model, enhancing vision-language modeling under a shared sequential prediction framework. By leveraging global context and relationship across the tokens, our method mitigates the error accumulation issue within the sequential generation. Experiments demonstrate that the proposed method improves the generation quality, enhancing the model{'}s ability to produce semantically consistent results."
}