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.
By Yuanhao Ban, I-Hung Hsu, Anastasios Angelopoulos, Wei-Lin Chiang, Ion Stoica, Cho-Jui Hsieh
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
arXiv:2606. 19162v1 Announce Type: new Abstract: Score- and flow-matching models often rely on preference-based reinforcement learning for two purposes: aligning with subjective preferences and, surprisingly, recovering properties such as visual realism and coherent object structure that matching-based training is intended to learn from the data itself.
By Nicolas Beltran-Velez, Felix Friedrich, Zhang Xiaofeng, Reyhane Askari-Hemmat, Xiaochuang Han, Adriana Romero-Soriano, Michal Drozdzal
arXiv:2605.13155v2 Announce Type: replace
Abstract: Text-to-image generation models have achieved remarkable progress in preference optimization, yet achieving robust alignment across diverse reward...
By Ying Ba, Tianyu Zhang, Mohan Zhou, Yalong Bai, Wenyi Mo, Guiwei Zhang, Bing Su, Ji-Rong Wen
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
The paper introduces Diffusion LAIR, a listwise preference optimization technique that leverages continuous reward scores instead of binary pairwise comparisons to align text‑to‑image diffusion models. LAIR transforms reward scores into centered advantage weights and optimizes an advantage‑weighted regression objective on an implicit reward defined by denoising‑loss improvement over a reference model, with a quadratic penalty to regulate reward magnitude. Experiments demonstrate that Diffusion LAIR surpasses strong baseline methods on SD1.5 and SDXL across generation, compositional, and editing tasks.
By Austin Wang, Jiaqi Han, Stefano Ermon, Yisong Yue
arXiv:2601. 12401v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) has emerged as a powerful paradigm for fine-tuning large-scale generative models, such as diffusion and flow models, to align with complex human preferences and user-specified tasks.
By Jinmei Liu, Haoru Li, Zhenhong Sun, Chaofeng Chen, Yatao Bian, Bo Wang, Daoyi Dong, Chunlin Chen, Zhi Wang
arXiv:2607. 14962v1 Announce Type: cross Abstract: Text-to-image (T2I) models can synthesize realistic, prompt-aligned images, yet samples generated for the same prompt often cover only a small subset of visually distinct modes.
By Ku Onoda, Paavo Parmas, Hiroki Furuta, Soichiro Nishimori, Yuta Oshima, Shohei Taniguchi, Yutaka Matsuo
CAST introduces a reinforcement‑learning fine‑tuning framework for diffusion models that addresses three key limitations: it automatically selects the denoising window based on each model’s trajectory, decomposes prompts into verifiable semantic atoms via Causal Scene Graphs, and applies atom‑level rewards spatially weighted in the policy objective. The method is applied to FLUX.2‑dev and Qwen‑Image‑2512, yielding up to 3.07× improvement on the hardest GenEval 2 prompts compared with Flow‑GRPO while also enhancing overall generation quality.
By Shu Yu, Chaochao Lu
arXiv:2607. 02291v1 Announce Type: new Abstract: Conventional reinforcement learning strategies for visual generation typically employ sample-wise reward functions, yet this practice frequently results in reward hacking that degrades image diversity and introduces visual anomalies.
By Ruihang Li, Mengde Xu, Shuyang Gu, Leigang Qu, Fuli Feng, Han Hu, Wenjie Wang
arXiv:2609.33803v2 Announce Type: replace-cross
Abstract: Reward models underpin the alignment of large language models, yet the dominant designs reduce each prompt--response pair to a point estimate...
By Xiangyang Wang, Bingxiang He, Zeyuan Liu, Jiaze Wang, Ziqing Qiao, Yuxin Zuo, Huan-ang Gao, Cheng Qian, Wenbin Zhang, Ran Li, Youbang Sun, Ning Ding, Yuanchun Shi, Zhiyuan Liu, Chaojun Xiao, Chun Yu
arXiv:2609.14896v1 Announce Type: cross
Abstract: A notable byproduct of LLM alignment training is mode collapse: the progressive loss of output diversity that narrows a model's expressivity at infer...
By Jiayi Yuan, Hangoo Kang, James Jihao Liu, Yejin Choi, Vikram Iyer, Liwei Jiang, Natasha Jaques