# On the Diffusibility of High-Dimensional Latents > Source: > Published: 2026-09-24 06:30:08+00:00 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 reco