# OmniAID: Decoupling Semantics and Artifacts for Universal AI-Generated Image Detection in the Wild

arXiv: https://arxiv.org/abs/2511.08423 · HTML: https://mlsanity.com/paper/2511.08423/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Placed in Vision mixture-of-experts, one of 12 directions in Mixture-of-experts.
- First posted on arXiv 11 Nov 2025.

## Placed in

- Mixture-of-experts / [Vision mixture-of-experts](https://mlsanity.com/moe/vision-mixture-of-experts/)

## Built on by (most cited first, 13 of 13)

- [Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence](https://mlsanity.com/paper/2607.07675/) (2026)
- [RealGen: Photorealistic Text-to-Image Generation via Detector-Guided Rewards](https://mlsanity.com/paper/2512.00473/) (2025)
- [FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection](https://mlsanity.com/paper/2605.30062/) (2026)
- [DailyBench: A Unified Benchmark for AI-Generated and Manipulated Images from Modern Generative Models](https://mlsanity.com/paper/2607.24016/) (2026)
- [Veritas++: Value-aware On-Policy Distillation for Perception-Enhanced AIGI Detection](https://mlsanity.com/paper/2607.27113/) (2026)
- [DreamHome-Pano: Design-Aware and Conflict-Free Panoramic Interior Generation](https://mlsanity.com/paper/2602.06494/) (2026)
- [HumanForge: A Human-Centric Deepfake Video Benchmark with Multi-Agent Forgery Rationales](https://mlsanity.com/paper/2607.08705/) (2026)
- [Temporal Concentration from Rollout Errors: Implicit Preference Optimization for Text-to-Video Diffusion](https://mlsanity.com/paper/2607.28058/) (2026)
- [FUSED: Forensic-Semantic Mixture-of-Experts for AI Inpainting Detection and Localization](https://mlsanity.com/paper/2608.28302/) (2026)
- [Editable Visual Design](https://mlsanity.com/paper/2609.04034/) (2026)
- [Beyond Natural Images: Rethinking AI-Generated Image Detection in Documents](https://mlsanity.com/paper/2609.14352/) (2026)
- [Forensic Twins: Self-Supervised Residual Learning for AI-Generated Image Forensics](https://mlsanity.com/paper/2609.31514/) (2026)
- [Certification of Real Images through Calibrated Content Authentication](https://mlsanity.com/paper/2610.05870/) (2026)

## Abstract (arXiv)

A truly universal AI-Generated Image (AIGI) detector must simultaneously generalize across diverse generative models and varied semantic content. Current methods learn a single, entangled forgery representation, conflating content-dependent flaws with content-agnostic artifacts, and are further constrained by outdated benchmarks. We propose OmniAID, a novel framework centered on a decoupled Mixture-of-Experts (MoE) architecture that separates: (1) semantic flaws across distinct content domains via Routable Specialized Semantic Experts, and (2) content-agnostic universal artifacts from content-dependent flaws via a Fixed Universal Artifact Expert. A two-stage training strategy first specializes experts independently with domain-specific hard-sampling, then trains a lightweight gating network for effective input routing. By explicitly decoupling "what is generated" (content-specific flaws) from "how it is generated" (universal artifacts), OmniAID achieves robust generalization. We also introduce Mirage, a large-scale, contemporary dataset comprising a modern training set and a challenging test set. Extensive experiments demonstrate that OmniAID surpasses existing detectors, establishing a new standard for AIGI detection against modern, in-the-wild threats. Code is available at https://github.com/yunncheng/OmniAID.