No AI summary available for this article.
Why It Matters
Representation Autoencoders (RAEs) enable diffusion models to operate in the feature spaces of pretrained visual encoders.
Provenance
Discovered via ArXiv and published by ArXiv.
Key Claims
Original description
Representation Autoencoders (RAEs) enable diffusion models to operate in the feature spaces of pretrained visual encoders. However, many off-the-shelf encoders are not optimized for faithful reconstruction, discarding fine-grained visual details. As expected, finetuning these encoders for image reconstruction recovers such details. However, perhaps counterintuitively, this procedure reduces the effective dimensionality of the resulting representation, and the altered geometry has downstream effects on generation. Specifically, we show that using the standard velocity prediction in flow matchin...
Discovered via ArXiv
Research papers and preprints from arXiv.
Publisher: arxiv.org
ID: http://arxiv.org/abs/2609.28473v1 · Indexed about 1 hour ago