Pengxiang Li
pengxiang
AI & ML interests
Video generation, Image editing, AD
Recent Activity
upvoted
a
paper
about 1 month ago
Bolmo: Byteifying the Next Generation of Language Models
upvoted
a
paper
about 1 month ago
PretrainZero: Reinforcement Active Pretraining
Organizations
-
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 • 66 -
OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generation
Paper • 2407.02371 • Published • 53 -
Large Language Diffusion Models
Paper • 2502.09992 • Published • 125
-
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 • 66 -
OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generation
Paper • 2407.02371 • Published • 53 -
Large Language Diffusion Models
Paper • 2502.09992 • Published • 125
models
15
pengxiang/DreamPara_think_out
Updated
pengxiang/DreamPara_think1_3step
Updated
pengxiang/DreamPara_think1
Updated
pengxiang/DreamPara_think1_3bs
Updated
pengxiang/DreamPara
8B
•
Updated
•
2
•
1
pengxiang/Qwen2.5-1.5B-Open-R1-Distill-loop
2B
•
Updated
pengxiang/Qwen2.5-1.5B-Open-R1-Distill
Text Generation
•
2B
•
Updated
•
1
pengxiang/Qwen2.5-1.5B-Open-R1-GRPO
Updated
pengxiang/LNS_1B
Updated
•
2
•
2
pengxiang/TrackDiffusion_SVD_Stage2
Text-to-Video
•
Updated
•
1
datasets
18
pengxiang/DreamPara_think_out
Updated
•
1
pengxiang/SFT_THINK
Viewer
•
Updated
•
319k
•
1
pengxiang/coins_new
Viewer
•
Updated
•
4.91k
•
779
pengxiang/COIN
Viewer
•
Updated
•
528
•
5
pengxiang/tvqa
Preview
•
Updated
pengxiang/COINs
Viewer
•
Updated
•
1.59k
•
588
pengxiang/sthv2
Updated
•
9
pengxiang/youcook2
Updated
•
38
pengxiang/UVO
Viewer
•
Updated
•
799
•
703
pengxiang/youcook
Viewer
•
Updated
•
407
•
21