The paper introduces ARRO, a reinforcement‑learning framework that enforces minimal‑change editing by auditing source images, instructions, and edited outputs for unimplemented and unintended changes. Using a vision‑language reward model and a group‑level rubric, ARRO achieves higher EditScore on multiple benchmarks and reduces off‑target pixel changes by 8.4% on FLUX.1 Kontext‑dev. The approach eliminates the need for per‑instruction human annotations and demonstrates strong performance across several evaluation sets.
RefineEdit is a training‑free prompt‑to‑prompt image editing framework that uses a Generative Refinement Network to edit images by refining binary image codes. It couples edit localization with content generation, selecting editable positions based on signed probability differences between an editing branch and a source branch, and stabilizes edits with adaptive spatial freezing and finite bit locking. The method requires no additional training, external masks, or attention control, and outperforms other methods on PIE‑Bench in background‑preservation metrics and CLIP scores.
By Yulong Chen, Ziqian Zhang, Haoyu Zhang, Ao He, Senmao Li, Kai Wang
arXiv:2605.08703v2 Announce Type: replace
Abstract: Aligning generative models with human preferences remains a central challenge. While RLHF is widely adopted, it relies on large-scale preference da...
By Yuxuan Zhang, Cong Wei, Penghui Du, Bo Li, Junwen Miao, Huaisong Zhang, Songcheng Cai, Yubo Wang, Dongfu Jiang, Yuyu Zhang, Changqian Yu, Ping Nie, Wenhu Chen, Kelsey R. Allen
arXiv:2610.16224v1 Announce Type: cross
Abstract: Text-to-image models have made remarkable progress in visual fidelity and instruction following, yet complex compositional generation remains challen...
By Zixu Wang, Xiaoran Zhao, Yahui Liu, Feng-ao Wang, Junhao Xiao, You Shu, Bing Liu, Yiting Liu, Songlei Jian, Zhiliang Tian, Dongsheng Li
arXiv:2606. 01213v1 Announce Type: cross Abstract: Despite tremendous recent progress, current text-guided image editing methods still struggle with many aspects of editing involving instruction following, minimally editing the source image, and ensuring high visual quality.
By Aishwarya Agrawal, Roy Hirsch, Yasumasa Onoe, Sherry Ben, Jason Baldridge
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