WorldEdit: Towards Open-World Image Editing with a Knowledge-Informed Benchmark

• URL: http://arxiv.org/abs/2602.07095v1
• Date: Fri, 06 Feb 2026 13:42:30 GMT
• Title: WorldEdit: Towards Open-World Image Editing with a Knowledge-Informed Benchmark
• Authors: Wang Lin, Feng Wang, Majun Zhang, Wentao Hu, Tao Jin, Zhou Zhao, Fei Wu, Jingyuan Chen, Alan Yuille, Sucheng Ren,
• Abstract summary: We introduce textbfWorldEdit, a dataset specifically designed to enable world-driven image editing.<n>WorldEdit consists of high-quality editing samples, guided by paraphrased instructions that align with real-world causal logic.<n>Our results show that the proposed dataset and methods significantly narrow the gap with GPT-4o and Nano-Banana.
• Score: 72.07273056097722
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Recent advances in image editing models have demonstrated remarkable capabilities in executing explicit instructions, such as attribute manipulation, style transfer, and pose synthesis. However, these models often face challenges when dealing with implicit editing instructions, which describe the cause of a visual change without explicitly detailing the resulting outcome. These limitations arise because existing models rely on uniform editing strategies that are not equipped to handle the complex world knowledge and reasoning required for implicit instructions. To address this gap, we introduce \textbf{WorldEdit}, a dataset specifically designed to enable world-driven image editing. WorldEdit consists of high-quality editing samples, guided by paraphrased instructions that align with real-world causal logic. Furthermore, we provide \textbf{WorldEdit-Test} for evaluating the existing model's performance on causal editing scenarios. With WorldEdit, we use a two-stage training framework for fine-tuning models like Bagel, integrating with a causal verification reward. Our results show that the proposed dataset and methods significantly narrow the gap with GPT-4o and Nano-Banana, demonstrating competitive performance not only in instruction following but also in knowledge plausibility, where many open-source systems typically struggle.

Related papers

• Charts Are Not Images: On the Challenges of Scientific Chart Editing [66.38730113476677]
  textitFigEdit is a benchmark for scientific figure editing comprising over 30,000 samples.<n>Our benchmark demonstrates the profound limitations of pixel-level manipulation.<n>By releasing textitFigEdit, we aim to enable systematic progress in structure-aware figure editing.
  arXiv  Detail & Related papers  (2025-11-30T06:13:48Z)
• SliderEdit: Continuous Image Editing with Fine-Grained Instruction Control [50.76070785417023]
  We introduce SliderEdit, a framework for continuous image editing with fine-grained, interpretable instruction control.<n>Given a multi-part edit instruction, SliderEdit disentangles the individual instructions and exposes each as a globally trained slider.<n>Our results pave the way for interactive, instruction-driven image manipulation with continuous and compositional control.
  arXiv  Detail & Related papers  (2025-11-12T20:21:37Z)
• SpotEdit: Evaluating Visually-Guided Image Editing Methods [3.5066378196008636]
  SpotEdit is a comprehensive benchmark designed to assess visually-guided image editing methods.<n>Our benchmark includes a dedicated component on hallucination, highlighting how leading models, such as GPT-4o, often hallucinate the existence of a visual cue and erroneously perform the editing task.
  arXiv  Detail & Related papers  (2025-08-25T16:08:57Z)
• Visual Autoregressive Modeling for Instruction-Guided Image Editing [97.04821896251681]
  We present a visual autoregressive framework that reframes image editing as a next-scale prediction problem.<n>VarEdit generates multi-scale target features to achieve precise edits.<n>It completes a $512times512$ editing in 1.2 seconds, making it 2.2$times$ faster than the similarly sized UltraEdit.
  arXiv  Detail & Related papers  (2025-08-21T17:59:32Z)
• Image Editing As Programs with Diffusion Models [69.05164729625052]
  We introduce Image Editing As Programs (IEAP), a unified image editing framework built upon the Diffusion Transformer (DiT) architecture.<n>IEAP approaches instructional editing through a reductionist lens, decomposing complex editing instructions into sequences of atomic operations.<n>Our framework delivers superior accuracy and semantic fidelity, particularly for complex, multi-step instructions.
  arXiv  Detail & Related papers  (2025-06-04T16:57:24Z)
• Better Call SAUL: Fluent and Consistent Language Model Editing with Generation Regularization [48.07144492109635]
  Large language models need to be updated regularly. Model editing is challenging as it might also affect knowledge that is unrelated to the new data. We propose SAUL, a streamlined model editing method that uses sentence concatenation with augmented random facts for generation regularization.
  arXiv  Detail & Related papers  (2024-10-03T12:28:13Z)
• EditWorld: Simulating World Dynamics for Instruction-Following Image Editing [68.6224340373457]
  Diffusion models have significantly improved the performance of image editing. We introduce world-instructed image editing, which defines and categorizes the instructions grounded by various world scenarios. Our method significantly outperforms existing editing methods in this new task.
  arXiv  Detail & Related papers  (2024-05-23T16:54:17Z)
• The Butterfly Effect of Model Editing: Few Edits Can Trigger Large Language Models Collapse [58.0132400208411]
  Even a single edit can trigger model collapse, manifesting as significant performance degradation in various benchmark tasks. benchmarking Large Language Models after each edit is impractically time-consuming and resource-intensive. We have utilized GPT-3.5 to develop a new dataset, HardEdit, based on hard cases.
  arXiv  Detail & Related papers  (2024-02-15T01:50:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.