-
Direct-a-Video: Customized Video Generation with User-Directed Camera Movement and Object Motion
Paper • 2402.03162 • Published • 19 -
ShortGPT: Layers in Large Language Models are More Redundant Than You Expect
Paper • 2403.03853 • Published • 63 -
OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generation
Paper • 2407.02371 • Published • 53
Pengxiang Li
pengxiang
AI & ML interests
Video generation, Image editing, AD
Recent Activity
liked
a dataset
3 days ago
turing-motors/CoVLA-Dataset
liked
a model
7 days ago
internlm/internlm3-8b-instruct
commented on
a paper
10 days ago
HybridNorm: Towards Stable and Efficient Transformer Training via Hybrid
Normalization
Organizations
None yet
Collections
1
models
7
pengxiang/LNS_1B
Updated
•
147
•
1
pengxiang/TrackDiffusion_SVD_Stage2
Text-to-Video
•
Updated
pengxiang/TrackDiffusion_SVD_Stage1
Text-to-Video
•
Updated
pengxiang/TrackDiffusion_Pretrain
Updated
•
2
•
1
pengxiang/GLIGEN_1_4
Updated
•
4
pengxiang/TrackDiffusion_ModelScope
Text-to-Video
•
Updated
pengxiang/trackdiffusion_ytvis
Text-to-Video
•
Updated
•
2