AIIC AI Intelligence Centre

SOURCE-LINKED INTELLIGENCE

On the Diffusibility of High-Dimensional Latents

arXiv · AI, language, vision and robotics · article · Sep 23, 2026 · UTC

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

Read original source ↗ Open in workspace

recordType
paper
region
Global

Evidence & attribution

First collected: 2026-09-24T08:22:30.429Z. This is not the publication date.