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: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
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
arXiv:2608.22780v1 Announce Type: new
Abstract: Reinforcement learning (RL) enables direct preference optimization for image editing through editing-specific rewards, which remain less developed due...
By Qichao Ma, Jikang Cheng, Ling Liang, Zhaofei Yu, Tiejun Huang, Renye Yan
arXiv:2610.29380v1 Announce Type: new
Abstract: Practical image generation requires both human preference alignment and few-step efficiency, yet combining reinforcement learning (RL) with distillatio...
By Sicong Kang, Fangao Zeng, Yuhan Li, Hao Zhou, Mengfei Xu, Wenxiang Shang, Wei Li, Bingbing Ni, Pipei Huang
arXiv:2607. 09492v1 Announce Type: new Abstract: Reinforcement learning (RL) is increasingly used to align multimodal large language models (MLLMs), but higher rewards do not always imply better task performance.
By Jiayu Yao, Yiwei Wang, Anmeng Zhang, Zhe Sun, Songsong Wang, Lingrui Mei, Yuyao Ge, Shenghua Liu
arXiv:2607. 01181v1 Announce Type: cross Abstract: RL with verifiable rewards (RLVR) has emerged as a powerful paradigm for training LMs on tasks with well-defined success metrics, such as code generation and mathematical reasoning.
By Mehul Damani, Isha Puri, Idan Shenfeld, Jacob Andreas
arXiv:2606. 03131v1 Announce Type: new Abstract: Reward models are central to large language model (LLM) alignment, but they remain vulnerable to reward hacking.
By Shuang Liu, Yuxuan Bo, Qiuyang Zhao, Caiyue Huang, Xiaorong Chen, Yanguang Liu, Mengnan Du
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
arXiv:2606. 27608v1 Announce Type: cross Abstract: We present Qwen-Image-2.
By Yixian Xu, Kaiyuan Gao, Yuxiang Chen, Yilei Chen, Zecheng Tang, Zihao Liu, Zikai Zhou, Deqing Li, Hao Meng, Kuan Cao, Jiahao Li, Jie Zhang, Liang Peng, Lihan Jiang, Ningyuan Tang, Shengming Yin, Tianhe Wu, Xiaoyue Chen, Yan Shu, Yanran Zhang, Yi Wang, Yu Wu, Yujia Wu, Zekai Zhang, Zhendong Wang, Xiao Xu, Kun Yan, Chenfei Wu
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
TikZilla is a new approach to generating TikZ code from textual descriptions, built on a larger, higher‑quality dataset called DaTikZ‑V4 that includes LLM‑generated figure descriptions. The method uses a two‑stage pipeline: supervised fine‑tuning of small Qwen models (3B and 8B) followed by reinforcement learning with an image encoder that provides semantically faithful reward signals. Human evaluations show that TikZilla outperforms its base models by 1.5–2 points on a 5‑point scale, beats GPT‑4o by 0.5 points, and matches GPT‑5 in image‑based tests while remaining much smaller.
By Christian Greisinger, Steffen Eger