Thinking-while-Generating: Interleaving Textual Reasoning throughout Visual Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Guo, Ziyu, Zhang, Renrui, Li, Hongyu, Zhang, Manyuan, Chen, Xinyan, Wang, Sifan, Feng, Yan, Pei, Peng, Heng, Pheng-Ann
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915628773801984
author Guo, Ziyu
Zhang, Renrui
Li, Hongyu
Zhang, Manyuan
Chen, Xinyan
Wang, Sifan
Feng, Yan
Pei, Peng
Heng, Pheng-Ann
author_facet Guo, Ziyu
Zhang, Renrui
Li, Hongyu
Zhang, Manyuan
Chen, Xinyan
Wang, Sifan
Feng, Yan
Pei, Peng
Heng, Pheng-Ann
contents Recent advances in visual generation have increasingly explored the integration of reasoning capabilities. They incorporate textual reasoning, i.e., think, either before (as pre-planning) or after (as post-refinement) the generation process, yet they lack on-the-fly multimodal interaction during the generation itself. In this preliminary study, we introduce Thinking-while-Generating (TwiG), the first interleaved framework that enables co-evolving textual reasoning throughout the visual generation process. As visual content is progressively generating, textual reasoning is interleaved to both guide upcoming local regions and reflect on previously synthesized ones. This dynamic interplay produces more context-aware and semantically rich visual outputs. To unveil the potential of this framework, we investigate three candidate strategies, zero-shot prompting, supervised fine-tuning (SFT) on our curated TwiG-50K dataset, and reinforcement learning (RL) via a customized TwiG-GRPO strategy, each offering unique insights into the dynamics of interleaved reasoning. We hope this work inspires further research into interleaving textual reasoning for enhanced visual generation. Code will be released at: https://github.com/ZiyuGuo99/Thinking-while-Generating.
format Preprint
id arxiv_https___arxiv_org_abs_2511_16671
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Thinking-while-Generating: Interleaving Textual Reasoning throughout Visual Generation
Guo, Ziyu
Zhang, Renrui
Li, Hongyu
Zhang, Manyuan
Chen, Xinyan
Wang, Sifan
Feng, Yan
Pei, Peng
Heng, Pheng-Ann
Computer Vision and Pattern Recognition
Artificial Intelligence
Computation and Language
Recent advances in visual generation have increasingly explored the integration of reasoning capabilities. They incorporate textual reasoning, i.e., think, either before (as pre-planning) or after (as post-refinement) the generation process, yet they lack on-the-fly multimodal interaction during the generation itself. In this preliminary study, we introduce Thinking-while-Generating (TwiG), the first interleaved framework that enables co-evolving textual reasoning throughout the visual generation process. As visual content is progressively generating, textual reasoning is interleaved to both guide upcoming local regions and reflect on previously synthesized ones. This dynamic interplay produces more context-aware and semantically rich visual outputs. To unveil the potential of this framework, we investigate three candidate strategies, zero-shot prompting, supervised fine-tuning (SFT) on our curated TwiG-50K dataset, and reinforcement learning (RL) via a customized TwiG-GRPO strategy, each offering unique insights into the dynamics of interleaved reasoning. We hope this work inspires further research into interleaving textual reasoning for enhanced visual generation. Code will be released at: https://github.com/ZiyuGuo99/Thinking-while-Generating.
title Thinking-while-Generating: Interleaving Textual Reasoning throughout Visual Generation
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2511.16671