Saved in:
Bibliographic Details
Main Authors: Lyu, Qiang, Chen, Zicong, Wang, Chongxiao, Shi, Haolin, Gao, Shibo, Piao, Ran, Zeng, Youwei, Si, Jianlou, Ding, Fei, Li, Jing, Lau, Chun Pong, Wang, Weiqiang
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.00743
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911294973542400
author Lyu, Qiang
Chen, Zicong
Wang, Chongxiao
Shi, Haolin
Gao, Shibo
Piao, Ran
Zeng, Youwei
Si, Jianlou
Ding, Fei
Li, Jing
Lau, Chun Pong
Wang, Weiqiang
author_facet Lyu, Qiang
Chen, Zicong
Wang, Chongxiao
Shi, Haolin
Gao, Shibo
Piao, Ran
Zeng, Youwei
Si, Jianlou
Ding, Fei
Li, Jing
Lau, Chun Pong
Wang, Weiqiang
contents Recently, Group Relative Policy Optimization (GRPO) has shown promising potential for aligning text-to-image (T2I) models, yet existing GRPO-based methods suffer from two critical limitations. (1) \textit{Shared credit assignment}: trajectory-level advantages derived from group-normalized sparse terminal rewards are uniformly applied across timesteps, failing to accurately estimate the potential of early denoising steps with vast exploration spaces. (2) \textit{Reward-mixing}: predefined weights for combining multi-objective rewards (e.g., text accuracy, visual quality, text color)--which have mismatched scales and variances--lead to unstable gradients and conflicting updates. To address these issues, we propose \textbf{Multi-GRPO}, a multi-group advantage estimation framework with two orthogonal grouping mechanisms. For better credit assignment, we introduce tree-based trajectories inspired by Monte Carlo Tree Search: branching trajectories at selected early denoising steps naturally forms \emph{temporal groups}, enabling accurate advantage estimation for early steps via descendant leaves while amortizing computation through shared prefixes. For multi-objective optimization, we introduce \emph{reward-based grouping} to compute advantages for each reward function \textit{independently} before aggregation, disentangling conflicting signals. To facilitate evaluation of multiple objective alignment, we curate \textit{OCR-Color-10}, a visual text rendering dataset with explicit color constraints. Across the single-reward \textit{PickScore-25k} and multi-objective \textit{OCR-Color-10} benchmarks, Multi-GRPO achieves superior stability and alignment performance, effectively balancing conflicting objectives. Code will be publicly available at \href{https://github.com/fikry102/Multi-GRPO}{https://github.com/fikry102/Multi-GRPO}.
format Preprint
id arxiv_https___arxiv_org_abs_2512_00743
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Multi-GRPO: Multi-Group Advantage Estimation for Text-to-Image Generation with Tree-Based Trajectories and Multiple Rewards
Lyu, Qiang
Chen, Zicong
Wang, Chongxiao
Shi, Haolin
Gao, Shibo
Piao, Ran
Zeng, Youwei
Si, Jianlou
Ding, Fei
Li, Jing
Lau, Chun Pong
Wang, Weiqiang
Computer Vision and Pattern Recognition
Recently, Group Relative Policy Optimization (GRPO) has shown promising potential for aligning text-to-image (T2I) models, yet existing GRPO-based methods suffer from two critical limitations. (1) \textit{Shared credit assignment}: trajectory-level advantages derived from group-normalized sparse terminal rewards are uniformly applied across timesteps, failing to accurately estimate the potential of early denoising steps with vast exploration spaces. (2) \textit{Reward-mixing}: predefined weights for combining multi-objective rewards (e.g., text accuracy, visual quality, text color)--which have mismatched scales and variances--lead to unstable gradients and conflicting updates. To address these issues, we propose \textbf{Multi-GRPO}, a multi-group advantage estimation framework with two orthogonal grouping mechanisms. For better credit assignment, we introduce tree-based trajectories inspired by Monte Carlo Tree Search: branching trajectories at selected early denoising steps naturally forms \emph{temporal groups}, enabling accurate advantage estimation for early steps via descendant leaves while amortizing computation through shared prefixes. For multi-objective optimization, we introduce \emph{reward-based grouping} to compute advantages for each reward function \textit{independently} before aggregation, disentangling conflicting signals. To facilitate evaluation of multiple objective alignment, we curate \textit{OCR-Color-10}, a visual text rendering dataset with explicit color constraints. Across the single-reward \textit{PickScore-25k} and multi-objective \textit{OCR-Color-10} benchmarks, Multi-GRPO achieves superior stability and alignment performance, effectively balancing conflicting objectives. Code will be publicly available at \href{https://github.com/fikry102/Multi-GRPO}{https://github.com/fikry102/Multi-GRPO}.
title Multi-GRPO: Multi-Group Advantage Estimation for Text-to-Image Generation with Tree-Based Trajectories and Multiple Rewards
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2512.00743