arxiv:2502.20321
Yi Jiang
JiangYi
AI & ML interests
visual generation
Large Language Models
Recent Activity
authored
a paper
about 1 month ago
DanceTrack: Multi-Object Tracking in Uniform Appearance and Diverse
Motion
authored
a paper
about 1 month ago
OmniTokenizer: A Joint Image-Video Tokenizer for Visual Generation
authored
a paper
about 1 month ago
Sparse R-CNN: End-to-End Object Detection with Learnable Proposals
Organizations
Papers
21
models
None public yet
datasets
None public yet