We introduce $\texttt{Complex-Edit}$, a comprehensive benchmark designed to systematically evaluate instruction-based image editing models across instructions of varying complexity. To develop this benchmark, we harness GPT-4o to automatically collect a diverse set of editing instructions at scale. Our approach follows a well-structured ``Chain-of-Edit'' pipeline: we first generate individual atomic editing tasks independently and then integrate them to form cohesive, complex instructions. Additionally, we introduce a suite of metrics to assess various aspects of editing performance, along with a VLM-based auto-evaluation pipeline that supports large-scale assessments. Our benchmark yields several notable insights: 1) Open-source models significantly underperform relative to proprietary, closed-source models, with the performance gap widening as instruction complexity increases; 2) Increased instructional complexity primarily impairs the models' ability to retain key elements from the input images and to preserve the overall aesthetic quality; 3) Decomposing a complex instruction into a sequence of atomic steps, executed in a step-by-step manner, substantially degrades performance across multiple metrics; 4) A straightforward Best-of-N selection strategy improves results for both direct editing and the step-by-step sequential approach; and 5) We observe a ``curse of synthetic data'': when synthetic data is involved in model training, the edited images from such models tend to appear increasingly synthetic as the complexity of the editing instructions rises -- a phenomenon that intriguingly also manifests in the latest GPT-4o outputs.
Beyond Textual CoT: Interleaved Text-Image Chains with Deep Confidence Reasoning for Image Editing
Shanghai Jiaotong University（上海交通大学）；Huawei Noah’s Ark Lab（华为诺亚实验室）；East China Normal University（华东师范大学）；Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（深圳先进技术研究院，中国科学院）
From Scale to Speed: Adaptive Test-Time Scaling for Image Editing
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络空间安全学院）；AMAP, Alibaba Group（阿里巴巴集团高德地图）；University of Queensland（昆士兰大学）
Leveraging Verifier-Based Reinforcement Learning in Image Editing
School of Computing and Data Science, The University of Hong Kong（计算与数据科学学院，香港大学）；Center for Embodied AI and Computer Vision, Shenzhen Loop Area Institute（具身人工智能与计算机视觉中心，深圳Loop Area研究院）
The Promise of RL for Autoregressive Image Editing
Mila – Quebec AI Institute（魁北克AI研究所）；Université de Montréal（蒙特利尔大学）；McGill University（麦吉尔大学）；École de Technologie Supérieure (ETS)（高等技术学院）；Polytechnique Montréal（蒙特利尔理工学院）；ServiceNow（ServiceNow公司）；Canada CIFAR AI Chair（加拿大CIFAR人工智能主席）
CoCo: Code as CoT for Text-to-Image Preview and Rare Concept Generation
South China University of Technology（南方科技大学）；StepFun；Institute of Automation Chinese Academy of Sciences（中国科学院自动化研究所）；Nanyang Technological University（南洋理工大学）；The Chinese University of Hong Kong（香港中文大学）
