Rethinking Patch Dependence for Masked Autoencoders — mentioned by gwern

Fri, 10 Oct 2025 19:56:07 GMT

This apparently doesn't apply here, but in fact, pixels can be generated independently of each other. There are architectures where you can generate an arbitrary pixel or element of the image without generating the others; they are just implicit. See NeRFs or 'single-pixel GANs' or MAEs: eg https://arxiv.org/abs/2003.08934 https://arxiv.org/abs/2011.13775 https://arxiv.org/abs/2401.14391 Why is this possible? I tend to think of it as reflecting the ability to 'memorize' all possible data, and the independent generation is just when you 'remember' a specific part of a memory. The latent space…

Paper and discussion history. A mention is not an endorsement.

Rethinking Patch Dependence for Masked Autoencoders · HackerPapers discussions

Rethinking Patch Dependence for Masked Autoencoders — mentioned by gwern