116 citations · 232 across the 6 of their papers we have counts for
6 papers
: Sparsifying Large Language Models via Dual Taylor Expansion and Attention Distribution Awareness
Lang Xiong, Ning Liu, Ao Ren +6
Large language models (LLMs) face significant deployment challenges due to their massive computational demands. % While pruning offers a promising compression solution, existing me…
Trustworthy Self-Attention: Enabling the Network to Focus Only on the Most Relevant References
Yu Jing, Tan Yujuan, Ren Ao +1
The prediction of optical flow for occluded points is still a difficult problem that has not yet been solved. Recent methods use self-attention to find relevant non-occluded points…
YOIO: You Only Iterate Once by mining and fusing multiple necessary global information in the optical flow estimation
Yu Jing, Tan Yujuan, Ren Ao +1
Occlusions pose a significant challenge to optical flow algorithms that even rely on global evidences. We consider an occluded point to be one that is imaged in the reference frame…
Flexible Clustered Federated Learning for Client-Level Data Distribution Shift
Moming Duan, Duo Liu, Xinyuan Ji +4
Federated Learning (FL) enables the multiple participating devices to collaboratively contribute to a global neural network model while keeping the training data locally. Unlike th…
CSAFL: A Clustered Semi-Asynchronous Federated Learning Framework
Yu Zhang, Moming Duan, Duo Liu +5
Federated learning (FL) is an emerging distributed machine learning paradigm that protects privacy and tackles the problem of isolated data islands. At present, there are two main…
FedSAE: A Novel Self-Adaptive Federated Learning Framework in Heterogeneous Systems
Li Li, Moming Duan, Duo Liu +5
Federated Learning (FL) is a novel distributed machine learning which allows thousands of edge devices to train model locally without uploading data concentrically to the server. B…