Cite
Notes
Only stored in your browser.
Attribution
Edge-MoE: Memory-Efficient Multi-Task Vision Transformer Architecture with Task-level Sparsity via Mixture-of-Experts
arXiv 2023
M$^3$ViT: Mixture-of-Experts Vision Transformer for Efficient Multi-task Learning with Model-Accelerator Co-design
arXiv 2022
from 2 papers
Hanxue Liang
Rishov Sarkar
Zhangyang Wang
Zhiwen Fan
Kai Zou
Tianlong Chen
Yu Cheng
Ziyu Jiang