https://derekwang2002.github.io/ai-intelligence/en/projects/pixelumm/ Material changes in AI models, agents, engineering and infrastructure, with primary sources and recommendations. en Mon, 02 Nov 2026 16:56:00 GMT https://derekwang2002.github.io/ai-intelligence/en/events/ev-20261001-02/ ev-20261001-02-published Fri, 02 Oct 2026 16:00:56 GMT New WATCH <p>The PixelUMM team released code and a 15.2B-parameter checkpoint for one autoregressive model that reads and generates images and video directly in pixel space. The design removes a separate vision encoder and VAE, but the public repository provides inference, evaluation and only a small illustrative training example. The checkpoint carries a noncommercial NVIDIA license.</p><p>Recommendation: WATCH</p><p>Sources: <a href="https://huggingface.co/nvidia/PixelUMM">NVIDIA PixelUMM model card</a> · <a href="https://github.com/nv-tlabs/PixelUMM">PixelUMM source repository</a> · <a href="https://arxiv.org/abs/2609.38597">PixelUMM paper</a></p>