Abstract We present Visual AutoRegressive modeling (VAR), a new generation paradigm
that redefines the autoregressive learning on images as coarse-to-fine" next-scale …

Masked (or absorbing) diffusion is actively explored as an alternative to autoregressive
models for generative modeling of discrete data. However, existing work in this area has …

Video diffusion models have made substantial progress in various video generation
applications. However, training models for long video generation tasks require significant …

Video generative models are receiving particular attention given their ability to generate
realistic and imaginative frames. Besides, these models are also observed to exhibit strong …

The recent development of Sora leads to a new era in text-to-video (T2V) generation. Along
with this comes the rising concern about its safety risks. The generated videos may contain …

In recent years, generative artificial intelligence has achieved significant advancements in
the field of image generation, spawning a variety of applications. However, video generation …

The most advanced diffusion models have recently adopted increasingly deep stacked
networks (eg, U-Net or Transformer) to promote the generative emergence capabilities of …

World models simulate future states of the world in response to different actions. They
facilitate interactive content creation and provides a foundation for grounded, long-horizon …

We present Infinity, a Bitwise Visual AutoRegressive Modeling capable of generating high-
resolution, photorealistic images following language instruction. Infinity redefines visual …

Variational Autoencoder (VAE), compressing videos into latent representations, is a crucial
preceding component of Latent Video Diffusion Models (LVDMs). With the same …