Junliang Guo

Fast Autoregressive Video Generation with Diagonal Decoding

Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modeling

Playing with Transformer at 30+ FPS via Next-Frame Diffusion

Video In-context Learning: Autoregressive Transformers are Zero-Shot Video Imitators

UniEdit: A Unified Tuning-Free Framework for Video Motion and Appearance Editing

IGOR: Image-GOal Representations are the Atomic Building Blocks for Next-Level Generalization in Embodied AI