Xiuye Gu

10

Papers

812

Total Citations

Papers (10)

Language Model Beats Diffusion - Tokenizer is key to visual generation

Photorealistic Video Generation with Diffusion Models

Language-Guided Image Tokenization for Generation

Interspecies Knowledge Transfer for Facial Keypoint Detection

HPLFlowNet: Hierarchical Permutohedral Lattice FlowNet for Scene Flow Estimation on Large-Scale Point Clouds

Scaling Open-Vocabulary Image Segmentation with Image-Level Labels

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

CLIP as RNN: Segment Countless Visual Concepts without Training Endeavor

Pixel-Aligned Language Model

DaTaSeg: Taming a Universal Multi-Dataset Multi-Task Segmentation Model