RoAR-VAE: Improving latent diffusability through robust prediction
RoAR-VAE improves the latent diffusability of visual tokenizers by predicting semantic features and reconstructing clean images from corrupted latents. Under the same training budget, its average performance on generation benchmarks is 2.19 points higher than the strongest baseline tokenizer, and its small-text reconstruction accuracy is 16.93 percentage points higher than FLUX.1-VAE.