Xiuye Gu

6

Papers

812

Total Citations

Papers (6)

Language Model Beats Diffusion - Tokenizer is key to visual generation

Photorealistic Video Generation with Diffusion Models

Language-Guided Image Tokenization for Generation

CLIP as RNN: Segment Countless Visual Concepts without Training Endeavor

Pixel-Aligned Language Model

VideoPoet: A Large Language Model for Zero-Shot Video Generation