Back to browse
I ported OmniAID image detection model to Apple's Neural Engine

I ported OmniAID image detection model to Apple's Neural Engine

by woadwarrior01·Apr 27, 2026·4 points·0 comments

AI Analysis

●●SolidSlickBig Brain

Runs OmniAID detection locally on Neural Engine instead of uploading your data to servers.

Strengths
  • Rewrote MoE architecture into static graph for Apple Neural Engine compatibility.
  • Zero data leaves the device, solving privacy concerns of cloud-based detectors.
  • Includes unicode cleanup tools to catch hidden AI text artifacts.
Weaknesses
  • AI detection is an arms race; accuracy degrades as models improve.
  • 418 MB model size is heavy for a utility app.
Category
Target Audience

iOS users, content moderators, privacy-conscious individuals

Similar To

GPTZero · Originality.ai · Hive Moderation

Post Description

OmniAID is a hybrid MoE detector, so the PyTorch model dynamically routes each image through top-k semantic experts plus a fixed artifact expert. For the CoreML/ANE port, I rewrote that into a static graph. Every low-rank SVD expert path is materialized and the router turns into a dense gate vector where unselected experts have zero weights. That makes the graph much more ANE friendly while preserving the model’s behavior closely enough to ship a w8a16 quantized CoreML model (~418 MB). The quantized model gets to ~94.24% accuracy on the Mirage-Test dataset (also from the OmniAID authors).

https://arxiv.org/abs/2511.08423

https://huggingface.co/datasets/Yunncheng/Mirage-Test

Similar Projects