Recent breakthroughs in instruction-based image editing have captured significant attention, as models are now capable of handling real-world editing demands with the practicality required by everyday users. However, editing models trained primarily for single-turn edits often break down in multi-turn editing--the natural interactive setting where a user iteratively refines an image based on the model's own previous outputs.
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
The paper investigates how fine‑grained credit assignment affects learning in multimodal agentic reinforcement learning, using video editing as a testbed. Four movie‑trailer editing tasks—Content Selection, Narrative Sequencing, Rough Cut, and Fine Cut—are introduced to represent real‑world editing workflows with varying complexity and horizon lengths. The study finds that decaying process rewards significantly boost performance on the long‑horizon Fine Cut task, while offering modest gains on shorter tasks; however, fixed process‑reward weighting can lead to reward‑hacking and degraded outcomes, and on‑policy self‑distillation provides limited benefit.
By Lei Zhao, Zongheng Cao, Xinyu Hu
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.
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
VibeEdit is a new image‑editing tool that lets users draw spatial marks and add brief notes directly on an image to create a canvas instruction. These instructions guide the model to perform tasks such as adding, removing, replacing, or moving objects, as well as modifying attributes, without needing a separate text prompt. The system is trained on 1.55 million annotated edit pairs and uses a layer‑decoupled conditioning approach, achieving higher VLM rubric scores and PSNR on a benchmark that tests target selection among similar objects.
By Jinjing Zhao, Fangyun Wei, Yitong Wang, Xiuyu Wu, Yunuo Chen, Yang Yue, Sirui Zhang, Wenbo Wang, Hongyang Zhang, Dong Chen, Yan Lu, Chang Xu
The paper introduces StruPO, a structure‑aware prompt editor that uses a calibrated scene graph to guide prompt modifications while preserving requested scene attributes. By aligning token edits with graph‑based structural feedback, StruPO learns a reusable editing policy that improves faithfulness and relational fidelity across multiple generation backbones. Experiments on diverse test sets and human studies show consistent gains in image quality and preference, especially for complex relations.
By Wentao Ye, Yali Ye, Zhiqing Xiao, Ru Peng, Xinpeng Ti, Liyao Li, Zhanming Shen, Peng Lu, Jie Zhang, Haobo Wang
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
The paper introduces Objective-aware Trajectory Credit Assignment (OTCA), a framework that refines reinforcement learning for diffusion-based visual generation. OTCA decomposes credit across denoising steps and allocates multiple reward signals adaptively, addressing the coarse, uniform reward assignment of existing GRPO pipelines. Experiments demonstrate that OTCA consistently enhances image and video generation quality across various metrics.
By Rui Li, Ke Hao, Yuanzhi Liang, Haibin Huang, Chi Zhang, Yun Gu, Xuelong Li
arXiv:2606. 05950v1 Announce Type: new Abstract: Text-guided image editing has advanced rapidly with diffusion models and unified multimodal foundation models.
By Yuxiao Ye, Haoran He, Fangyuan Kong, Xintao Wang, Pengfei Wan, Kun Gai, Ling Pan
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
CoinVE-200K is a large, high‑quality dataset for compositional instruction‑guided video editing, featuring 1080p video‑editing pairs up to 201 frames long and containing 2–5 atomic editing operations per sample. The dataset covers diverse editing intents—targeting humans, objects, and backgrounds with addition, removal, modification, and stylization—while ensuring instruction faithfulness, visual quality, temporal consistency, and compositional diversity through a careful generation and filtering pipeline. CoinVE-Bench benchmarks these capabilities, and CoinVE-Edit, a 22B model built on Wan2.1‑T2V‑14B and Qwen3‑VL‑8B‑Instruct, demonstrates strong performance in instruction following, compositional editing accuracy, visual quality, and temporal consistency.