14 citations · 16 across the 7 of their papers we have counts for
7 papers
RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers
Xuwei Xu, Yang Li, Yudong Chen +2
We reveal that feedforward network (FFN) layers, rather than attention layers, are the primary contributors to Vision Transformer (ViT) inference latency, with their impact signify…
DARLR: Dual-Agent Offline Reinforcement Learning for Recommender Systems with Dynamic Reward
Yi Zhang, Ruihong Qiu, Xuwei Xu +2
Model-based offline reinforcement learning (RL) has emerged as a promising approach for recommender systems, enabling effective policy learning by interacting with frozen world mod…
No Token Left Behind: Efficient Vision Transformer via Dynamic Token Idling
Xuwei Xu, Changlin Li, Yudong Chen +3
Vision Transformers (ViTs) have demonstrated outstanding performance in computer vision tasks, yet their high computational complexity prevents their deployment in computing resour…
GTP-ViT: Efficient Vision Transformers via Graph-based Token Propagation
Xuwei Xu, Sen Wang, Yudong Chen +3
Vision Transformers (ViTs) have revolutionized the field of computer vision, yet their deployments on resource-constrained devices remain challenging due to high computational dema…
Understanding the Effects of Projectors in Knowledge Distillation
Yudong Chen, Sen Wang, Jiajun Liu +4
Conventionally, during the knowledge distillation process (e.g. feature distillation), an additional projector is often required to perform feature transformation due to the dimens…
Plug n' Play: Channel Shuffle Module for Enhancing Tiny Vision Transformers
Xuwei Xu, Sen Wang, Yudong Chen +1
Vision Transformers (ViTs) have demonstrated remarkable performance in various computer vision tasks. However, the high computational complexity hinders ViTs' applicability on devi…
Improved Feature Distillation via Projector Ensemble
Yudong Chen, Sen Wang, Jiajun Liu +3
In knowledge distillation, previous feature distillation methods mainly focus on the design of loss functions and the selection of the distilled layers, while the effect of the fea…