This paper presents Diffusion Forcing, a new training paradigm where a diffusion model is
trained to denoise a set of tokens with independent per-token noise levels. We apply …

Autoregressive models (ARMs) and diffusion models (DMs) represent two leading
paradigms in generative modeling, each excelling in distinct areas: ARMs in global context …

Current video diffusion models achieve impressive generation quality but struggle in
interactive applications due to bidirectional attention dependencies. The generation of a …

The control problems of complex physical systems have broad applications in science and
engineering. Previous studies have shown that generative control methods based on …

Modelling partial differential equations (PDEs) is of crucial importance in science and
engineering, and it includes tasks ranging from forecasting to inverse problems, such as …

The recent surge of interest in comprehensive multimodal models has necessitated the
unification of diverse modalities. However, the unification suffers from disparate …

We introduce OneDiffusion, a versatile, large-scale diffusion model that seamlessly supports
bidirectional image synthesis and understanding across diverse tasks. It enables conditional …

Efficiently compressing high-dimensional audio signals into a compact and informative
latent space is crucial for various tasks, including generative modeling and music …

Audio language models have recently emerged as a promising approach for various audio
generation tasks, relying on audio tokenizers to encode waveforms into sequences of …

Despite the considerable progress achieved in the long video generation problem, there is
still significant room to improve the consistency of the videos, particularly in terms of …