# RoAR-VAE: Improving Latent Diffusability through Robust Prediction > Source: > Published: 2026-10-20 03:00:09+00:00 An effective visual tokenizer must preserve image fidelity while producing latents that downstream diffusion models can learn efficiently. Prior work improves latent diffusability through semantic alignment or joint tokenizer--diffusion training. Revisiting REPA-E, a representative approach, we find