Seonglae ChoFeature Auto-Encoder
One Layer Is Enough: Adapting Pretrained Visual Encoders for Image Generation
One Layer Is Enough: Adapting Pretrained Visual Encoders for Image...
Visual generative models (e.g., diffusion models) typically operate in compressed latent spaces to balance training efficiency and sample quality. In parallel, there has been growing interest in...
https://arxiv.org/abs/2512.07829
