Diffusion training drops the external vision encoder: reusing VAE features cuts SiT-XL/2 FID from 17.2 to 7.4
CoVA recomposes the generative model's own VAE reconstruction features online into supervision with stronger semantics and spatial structure, cutting SiT-XL/2 FID on ImageNet 256x256 from 17.2 to 7.4 without an external vision encoder.