# Can We Model the Artifacts Explicitly? Disentangle Artifacts via Pairwise Edit Relations for Image Manipulation Localization

arXiv: https://arxiv.org/abs/2610.07916 · HTML: https://mlsanity.com/paper/2610.07916/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 65 references that are in the map.
- First posted on arXiv 6 Oct 2026.

## Builds on (most cited first, 11 of 11)

- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [Qwen-Image Technical Report](https://mlsanity.com/paper/2508.02324/) (2025)
- [Gemini: A Family of Highly Capable Multimodal Models](https://mlsanity.com/paper/2312.11805/) (2023)
- [Seedream 4.0: Toward Next-generation Multimodal Image Generation](https://mlsanity.com/paper/2509.20427/) (2025)
- [IML-ViT: Benchmarking Image Manipulation Localization by Vision Transformer](https://mlsanity.com/paper/2307.14863/) (2023)
- [RAM: Recover Any 3D Human Motion in-the-Wild](https://mlsanity.com/paper/2603.19929/) (2026)
- [Venus-DeFakerOne: Unified Fake Image Detection & Localization](https://mlsanity.com/paper/2605.14091/) (2026)
- [PASA: A Principled Embedding-Space Watermarking Approach for LLM-Generated Text under Semantic-Invariant Attacks](https://mlsanity.com/paper/2605.10977/) (2026)
- [Beyond Semantic Features: Pixel-level Mapping for Generalized AI-Generated Image Detection](https://mlsanity.com/paper/2512.17350/) (2025)
- [A/B Agent: A Self-Evolving Agent for Strategy Iteration in Industrial A/B Testing](https://mlsanity.com/paper/2608.04625/) (2026)

## Abstract (arXiv)

Image Manipulation Localization (IML) is commonly formulated as a fully supervised learning task that estimates the optimal manipulation mask y for a given image x. In this work, we first reveal the latent nature of artifacts and thus reinterpret IML as a latent-variable problem, P(y|x)=int P(y|z),P(z|x),dz, where z denotes the artifacts. Following this interpretation, we pinpoint the cause for the current IML models' insufficiency as their implicit artifacts modeling strategy, highlighting the necessity of modeling z in an explicit manner. Without direct labels, feature disentanglement is the most appropriate solution for this explicit modeling. Accordingly, we propose a two-stage learning paradigm with the Pairwise Artifacts Learning (PAL) and Standard Localization (SL) phases to estimate P(z|x) and P(y|z) via edit relations. To support our edit-relation-based learning, we further curate EditGroup-45K, a source-anchored dataset organized into edit groups for pair construction. Extensive experiments show that our PAL paradigm yields consistent improvements across diverse IML architectures, and empirical analyses further verify that PAL does capture artifacts explicitly through feature disentanglement. Code and dataset are available at https://github.com/venus-guangjian/PAL