Sample By Step, Optimize By Chunk: Chunk-Level GRPO For Text-to-Image Generation

Yifu Luo, Penghui Du, libo, Sinan Du, Tiantian Zhang, Yongzhe Chang, Wu Kai, Kun Gai, Xueqian Wang

Sample By Step, Optimize By Chunk: Chunk-Level GRPO For Text-to-Image Generation: 20 upvotes on Hugging Face Daily Papers, #6 of 26 papers on 2025-10-27. Day-by-day upvote history. It lost 11 votes when the Hub removed votes in bulk.

Group Relative Policy Optimization (GRPO) has shown strong potential for flow-matching-based text-to-image (T2I) generation, but it faces two key limitations: inaccurate advantage attribution, and the neglect of temporal dynamics of generation. In this work, we argue that shifting the optimization paradigm from the step level to the chunk level can effectively alleviate these issues. Building on this idea, we propose Chunk-GRPO, the first chunk-level GRPO-based approach for T2I generation. The insight is to group consecutive steps into coherent 'chunk's that capture the intrinsic temporal dynamics of flow matching, and to optimize policies at the chunk level. In addition, we introduce an optional weighted sampling strategy to further enhance performance. Extensive experiments show that ChunkGRPO achieves superior results in both preference alignment and image quality, highlighting the promise of chunk-level optimization for GRPO-based methods.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.