28 citations · 37 across the 16 of their papers we have counts for
3 papers · 1 filter
FedYolo: Augmenting Federated Learning with Pretrained Transformers
Xuechen Zhang, Mingchen Li, Xiangyu Chang +4
The growth and diversity of machine learning applications motivate a rethinking of learning with mobile and edge devices. How can we address diverse client goals and learn with sca…
Max-Margin Token Selection in Attention Mechanism
Davoud Ataee Tarzanagh, Yingcong Li, Xuechen Zhang +1
Attention mechanism is a central component of the transformer architecture which led to the phenomenal success of large language models. However, the theoretical principles underly…
Learning on Manifolds: Universal Approximations Properties using Geometric Controllability Conditions for Neural ODEs
Karthik Elamvazhuthi, Xuechen Zhang, Samet Oymak +1
In numerous robotics and mechanical engineering applications, among others, data is often constrained on smooth manifolds due to the presence of rotational degrees of freedom. Comm…