Accelerating Diffusion Decoders via Multi-Scale Sampling and One-Step Distillation

ArXi:2603.19570v1 Announce Type: new Image tokenization plays a central role in modern generative modeling by mapping visual inputs into compact representations that serve as an intermediate signal between pixels and generative models. Diffusion-based decoders have recently been adopted in image tokenization to reconstruct images from latent representations with high perceptual fidelity. In contrast to diffusion models used for downstream generation, these decoders are dedicated to faithful reconstruction rather than content generation. However, their iterative sampling process