https://hackerpaper.kaipfister.de/p/2511.08423/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMThttps://news.ycombinator.com/item?id=47921042urn:hackerpapers:submission:2511.08423:47921042Mon, 27 Apr 2026 13:03:47 GMT<p>Show HN: I ported OmniAID image detection model to Apple&#x27;s Neural Engine</p><p>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).…</p><p>4 points; 0 discussion replies on HN. <a href="https://hackerpaper.kaipfister.de/p/2511.08423/">Paper and source history</a>. A submission is not an endorsement.</p>cs.CVhttps://news.ycombinator.com/item?id=47856090urn:hackerpapers:mention:2511.08423:47856090Tue, 21 Apr 2026 23:15:26 GMT<p>Yeah, OpenAI has been attaching C2PA manifests to all their generated images from the very beginning. Also, based on a small evaluation that I ran, modern ML based AI generated image detectors like OmniAID[1] seem to do quite well at detecting GPT-Image-2 generated images. I use both in an on-device AI generated image detector that I built. [1]: https://arxiv.org/abs/2511.08423</p><p><a href="https://hackerpaper.kaipfister.de/p/2511.08423/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CV