Jiarui Xu

Latest

• One-Minute Video Generation with Test-Time Training
• Parallel Sequence Modeling via Generalization Spatial Propagation Network (GSPN)
• Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models
• GPViT: A High Resolution Non-Hierarchical Vision Transformer with Group Propagation
• GroupViT: Semantic Segmentation Emerges From Text Supervision