# Unifying Semantic Priors and High-Frequency Traces: Enhancing V-JEPA with Mixture-of-Experts for Robust Synthetic Image Forensics

arXiv: https://arxiv.org/abs/2609.16778 · HTML: https://mlsanity.com/paper/2609.16778/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Multimodal MoE models, one of 12 directions in Mixture-of-experts.
- Builds on 29 of its 43 references that are in the map.
- First posted on arXiv 15 Sep 2026.

## Placed in

- Mixture-of-experts / [Multimodal MoE models](https://mlsanity.com/moe/multimodal-moe-models/)

## Builds on (most cited first, 29 of 29)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture](https://mlsanity.com/paper/2301.08243/) (2023)
- [FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space](https://mlsanity.com/paper/2506.15742/) (2025)
- [CNN-generated images are surprisingly easy to spot... for now](https://mlsanity.com/paper/1912.11035/) (2019)
- [V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning](https://mlsanity.com/paper/2506.09985/) (2025)
- [Revisiting Feature Prediction for Learning Visual Representations from Video](https://mlsanity.com/paper/2404.08471/) (2024)
- [Leveraging Frequency Analysis for Deep Fake Image Recognition](https://mlsanity.com/paper/2003.08685/) (2020)
- [Towards Universal Fake Image Detectors that Generalize Across Generative Models](https://mlsanity.com/paper/2302.10174/) (2023)
- [MesoNet: a Compact Facial Video Forgery Detection Network](https://mlsanity.com/paper/1809.00888/) (2018)
- [DIRE for Diffusion-Generated Image Detection](https://mlsanity.com/paper/2303.09295/) (2023)
- [GenImage: A Million-Scale Benchmark for Detecting AI-Generated Image](https://mlsanity.com/paper/2306.08571/) (2023)
- [Global Texture Enhancement for Fake Face Detection in the Wild](https://mlsanity.com/paper/2002.00133/) (2020)
- [PatchCraft: Exploring Texture Patch for Efficient AI-generated Image Detection](https://mlsanity.com/paper/2311.12397/) (2023)
- [M2TR: Multi-modal Multi-scale Transformers for Deepfake Detection](https://mlsanity.com/paper/2104.09770/) (2021)
- [SIDA: Social Media Image Deepfake Detection, Localization and Explanation with Large Multimodal Model](https://mlsanity.com/paper/2412.04292/) (2024)
- [Protecting Celebrities from DeepFake with Identity Consistency Transformer](https://mlsanity.com/paper/2203.01318/) (2022)
- [Fusing Global and Local Features for Generalized AI-Synthesized Image Detection](https://mlsanity.com/paper/2203.13964/) (2022)
- [UIA-ViT: Unsupervised Inconsistency-Aware Method based on Vision Transformer for Face Forgery Detection](https://mlsanity.com/paper/2210.12752/) (2022)
- [AntifakePrompt: Prompt-Tuned Vision-Language Models are Fake Image Detectors](https://mlsanity.com/paper/2310.17419/) (2023)
- [Residual Mixture of Experts](https://mlsanity.com/paper/2204.09636/) (2022)
- [MoE-FFD: Mixture of Experts for Generalized and Parameter-Efficient Face Forgery Detection](https://mlsanity.com/paper/2404.08452/) (2024)
- [Detecting Generated Images by Real Images Only](https://mlsanity.com/paper/2311.00962/) (2023)
- [A Timely Survey on Vision Transformer for Deepfake Detection](https://mlsanity.com/paper/2405.08463/) (2024)
- [On DeepSeekMoE: Statistical Benefits of Shared Experts and Normalized Sigmoid Gating](https://mlsanity.com/paper/2505.10860/) (2025)

## Abstract (arXiv)

The unchecked proliferation of manipulated images on social media platforms has increased the spread of misinformation, posing a severe threat to public trust and information integrity. Modern deepfake detectors typically rely on Vision Transformers (ViTs) to capture the low-level inconsistencies that characterize fully synthetic or locally tampered images. However, the global understanding of such foundation models is not enough to discriminate alone between real and fake multimedia content, especially in challenging scenarios where images are compressed or transmitted through social media. In this paper we pioneer the application of Joint-Embedding Predictive Architecture (JEPA) models to deepfake detection, taking advantage of the generalized representation of visual reality that such World Models have exhibited. We hypothesize, and empirically demonstrate, that the intrinsic world understanding of JEPA models can be used as a strong prior for a deepfake detector. To fully exploit JEPA capabilities, we propose MoE-JEPA, a dual-stream architecture for deepfake detection. By enhancing a V-JEPA 2 backbone with a Residual Mixture-of-Experts (MoE) mechanism, along with a noise stream branch, our model dynamically internalizes forensic knowledge. Furthermore, a Gated Attention Multiple Instance Learning (MIL) module is employed to ensure precise spatial semantic understanding. Evaluated on the SID-Set benchmark, comprising 300K AI-generated, tampered and authentic images, MoE-JEPA establishes a new state-of-the-art with an accuracy of 95.54%, successfully outperforming vastly larger models.