arXiv AI October 5, 2026 By Yuanhao Ban, I-Hung Hsu, Anastasios Angelopoulos, Wei-Lin Chiang, Ion Stoica, Cho-Jui Hsieh

Post-Training Frontier Text-to-Image Models by Composing Preference and Rubric Rewards

The paper presents a post‑training approach for text‑to‑image models that combines a preference reward, trained on large human preference data, with rubric‑based rewards that assess prompt faithfulness and other desirable traits. The authors show that a simple reward composition strategy outperforms a naive weighted average, leading to significant Elo gains on the Arena leaderboard for models like Flux2dev and Ideogram‑4. They also release Arena‑T2I‑Training, a 1K subset of data to aid reproducible research in post‑training.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI

Jun 17

STAR: SpatioTemporal Adaptive Reward Allocation for Text-to-Image RL Post-Training

arXiv:2606. 17979v1 Announce Type: new Abstract: Existing RL post-training methods for text-to-image generation usually convert the final-image reward into a single scalar advantage and apply it with the same strength to the entire generative trajectory.

By Jinjie Shen, Wei Deng, Xian Hu, Daiguo Zhou, Jian Luan

diffusion computer-vision reinforcement-learning safety

arXiv Computer Vision

Sep 1

Understanding Reward Hacking in Text-to-Image Reinforcement Learning

arXiv:2601.03468v2 Announce Type: replace Abstract: Reinforcement learning (RL) has become a standard approach for post-training large language models and, more recently, for improving image generati...

By Yunqi Hong, Kuei-Chun Kao, Hengguang Zhou, Cho-Jui Hsieh

llms diffusion reinforcement-learning safety

arXiv Computer Vision

Aug 28

RubricRM: Generative Reward Modeling via Dynamic Rubrics for Image Generation and Editing

RubricRM introduces a pairwise generative reward modeling framework that generates an input‑specific rubric—comprising evaluation dimensions, weights, and scoring criteria—to score candidate images. The method is trained in two stages: supervised fine‑tuning to learn the rubric‑based scoring paradigm and GRPO to refine dimension‑level rewards. Experiments on text‑to‑image generation and instruction‑based image editing benchmarks demonstrate that RubricRM outperforms existing specialized reward models and competes with strong proprietary MLLM judges while using smaller backbones.

By Zijian Kan, Wei Wang, Long Luo, Bing Zhao, Xuan Ren, Weixu Qiao, Wenbo Li, Hu Wei, Lin Qu

diffusion reinforcement-learning fine-tuning benchmarks safety

arXiv AI

Jul 20

Debiasing Text-to-Image Evaluation via Implicit Cultural Alignment Reward Modeling

arXiv:2607. 15740v1 Announce Type: cross Abstract: As Text-to-Image (T2I) systems rapidly advance, evaluating the cultural authenticity of synthesized content has become increasingly important for fair and trustworthy generative AI.

By Bo-An Chang, Yu-Chih Chen

llms diffusion nlp reinforcement-learning multimodal benchmarks safety

arXiv Computation and Language

Sep 30

POET: Preference Optimization for Enhanced Text-to-Image Generation

arXiv:2510.12041v3 Announce Type: replace Abstract: Recent advances in text-to-image (T2I) generation have achieved impressive results, yet existing models often struggle with simple or underspecifie...

By Ruibo Chen, Jiacheng Pan, Heng Huang, Zhenheng Yang

llms diffusion reinforcement-learning fine-tuning multimodal benchmarks safety

arXiv AI

Jul 1

Arena-T2I Hard: Benchmarking and Improving Faithfulness with Dependency-Aware Checklist

arXiv:2606. 31711v1 Announce Type: new Abstract: Faithfulness -- how precisely a generated image aligns with its prompt -- is increasingly central to the real-world utility of text-to-image (T2I) models.

By Yuanhao Ban, Tong Xie, Sohyun An, Yunqi Hong, Evan Frick, I-Hung Hsu, Wei-Lin Chiang, Ion Stoica, Cho-Jui Hsieh

diffusion multimodal benchmarks

One email a morning, machine-written

Related stories

STAR: SpatioTemporal Adaptive Reward Allocation for Text-to-Image RL Post-Training

Understanding Reward Hacking in Text-to-Image Reinforcement Learning

RubricRM: Generative Reward Modeling via Dynamic Rubrics for Image Generation and Editing

Debiasing Text-to-Image Evaluation via Implicit Cultural Alignment Reward Modeling

POET: Preference Optimization for Enhanced Text-to-Image Generation

Arena-T2I Hard: Benchmarking and Improving Faithfulness with Dependency-Aware Checklist