@inproceedings{zhou-etal-2026-unified,
    title = "Unified Thinker: A General Reasoning Core for Image Generation",
    author = "Zhou, Sashuai  and
      Zhou, Qiang  and
      Hu, Jijin  and
      Yang, Hanqing  and
      Cao, Yue  and
      Ma, Junpeng  and
      Ma, Yinchao  and
      Song, Jun  and
      Ge, Tiezheng  and
      Yu, Cheng  and
      Zheng, Bo  and
      Zhao, Zhou",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.484/",
    pages = "10597--10613",
    ISBN = "979-8-89176-390-6",
    abstract = "Despite impressive progress in high-fidelity image synthesis, generative models still struggle with logic-intensive instruction following, exposing a persistent reasoning{--}execution gap. Meanwhile, closed-source systems (e.g., Nano Banana) have demonstrated strong reasoning-driven image generation, highlighting a substantial gap to current open-source models. We argue that closing this gap requires not merely better visual generators, but executable reasoning: decomposing high-level intents into grounded, verifiable plans that directly steer the generative process. To this end, we propose \textbf{Unified Thinker}, a task-agnostic reasoning architecture for general image generation, designed as a unified planning core that can plug into diverse generators and workflows. Unified Thinker decouples a dedicated Thinker from the image Generator, enabling modular upgrades of reasoning without retraining the entire generative model. We further introduce a two-stage training paradigm: we first build a structured planning interface for the Thinker, then apply reinforcement learning to ground its policy in pixel-level feedback, encouraging plans that optimize visual correctness over textual plausibility. Extensive experiments on text-to-image generation and image editing show that Unified Thinker substantially improves image reasoning and generation quality."
}