3 papers
cs.CV2025
NeuMatC: A General Neural Framework for Fast Parametric Matrix Operation
Chuan Wang, Xi-le Zhao, Zhilong Han +3
Matrix operations (e.g., inversion and singular value decomposition (SVD)) are fundamental in science and engineering. In many emerging real-world applications (such as wireless co…
cs.LG2024
Gradient Projection For Continual Parameter-Efficient Tuning
Jingyang Qiao, Zhizhong Zhang, Xin Tan +4
Parameter-efficient tunings (PETs) have demonstrated impressive performance and promising perspectives in training large models, while they are still confronted with a common probl…
cs.CV2015
Video Primal Sketch: A Unified Middle-Level Representation for Video
Zhi Han, Zongben Xu, Song-Chun Zhu
This paper presents a middle-level video representation named Video Primal Sketch (VPS), which integrates two regimes of models: i) sparse coding model using static or moving primi…