Cite
Notes
Only stored in your browser.
Attribution
CyberV: Cybernetics for Test-time Scaling in Video Understanding
arXiv 2025
Robot Learning from a Physical World Model
Is synthetic data from generative models ready for image recognition?
arXiv 2022
TransMix: Attend to Mix for Vision Transformers
CVPR 2022 1
from 4 papers
Philip Torr
Song Bai
Alan Yuille
Chuhui Xue
Hao-Ning Wu
Howard Zhou
Huizhong Chen
Jiageng Mao
Jiahao Meng
Jie-Neng Chen