Uni-Edit: Intelligent Editing Is A General Task For Unified Model Tuning
Summary
Uni-Edit proposes using intelligent image editing as a single general task to simultaneously improve unified multimodal models' understanding, generation, and editing capabilities, with an automated data synthesis pipeline creating complex editing instructions.
View Cached Full Text
Cached at: 05/21/26, 06:20 AM
Paper page - Uni-Edit: Intelligent Editing Is A General Task For Unified Model Tuning
Source: https://huggingface.co/papers/2605.21487
Abstract
Uni-Edit introduces an intelligent image editing task that simultaneously enhances unified multimodal models’ understanding, generation, and editing capabilities through a single training stage and dataset, utilizing an automated data synthesis pipeline for complex editing instructions.
Currently, enhancingUnified Multimodal Models(UMMs) with image understanding, generation, and editing capabilities mainly relies on mixedmulti-task training. Due to inherent task conflicts, such strategy requires complex multi-stage pipelines, massive data mixing, and balancing tricks, merely resulting in a performance trade-off rather than true mutual reinforcement. To break this paradigm, we propose Uni-Edit, an intelligentimage editingtask that serves as the first general task for UMM tuning. Unlike complex mixed pipelines, Uni-Edit improves performance across all three abilities at once using only one task, one training stage, and one dataset. Specifically, we first identifyimage editingas an inherently ideal general task, as it naturally demands both visual understanding and generation. However, existing editing data relies on simplistic instructions that severely underutilize a model’s understanding capacity. To address this, we introduce the first automated and scalabledata synthesis pipelinefor intelligent editing, transforming diverseVQA datainto complex and effective editing instructions with embedded questions and nested logic. This yields Uni-Edit-148k, pairing diversereasoning-intensive instructionswith high-quality edited images. Extensive experiments onBAGELandJanus-Prodemonstrate that tuning solely on Uni-Edit achieves comprehensive enhancements across all three capabilities without any auxiliary operations.
View arXiv pageView PDFProject pageGitHub2Add to collection
Models citing this paper1
Datasets citing this paper1
#### Uni-Edit/Train-Data Viewer• Updatedabout 4 hours ago • 8.39k • 24
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2605.21487 in a Space README.md to link it from this page.
Collections including this paper0
No Collection including this paper
Add this paper to acollectionto link it from this page.
Similar Articles
Do Text Edits Generalize to Visual Generation? Benchmarking Cross-Modal Knowledge Editing in UMMs
This paper introduces UniKE, the first benchmark for cross-modal knowledge editing in unified multimodal models (UMMs), revealing a significant modality gap where text edits achieve 92% efficacy but only 18.5% transfer to image generation. It proposes Reasoning-augmented Parameter Editing to improve cross-modal transfer, with gains up to 18.6 percentage points.
Steering Visual Generation in Unified Multimodal Models with Understanding Supervision
This paper introduces UNO, an Understanding-Oriented Post-Training framework that uses comprehension tasks as supervisory signals to enhance image generation and editing in unified multimodal models.
UniCorn: Towards Self-Improving Unified Multimodal Models through Self-Generated Supervision
UniCorn is a framework that enables unified multimodal models to self-improve by using a multi-agent system for prompt generation, image creation, and quality evaluation, achieving state-of-the-art results on text-to-image benchmarks like TIIF, WISE, and OneIG-EN.
Unified Multimodal Autoregressive Modeling with Shared Context-Visual Tokenizer is Key to Unification
UniAR presents a unified autoregressive framework that uses a single discrete visual tokenizer to bridge visual understanding and generation, achieving state-of-the-art results in image generation and editing.
UniPath: Adaptive Coordination of Understanding and Generation for Unified Multimodal Reasoning
UniPath proposes a framework for adaptive coordination of understanding and generation in unified multimodal models, leveraging coordination-path diversity to improve performance over fixed strategies.