50 citations · 92 across the 16 of their papers we have counts for
6 papers · 1 filter
Dynamic Sparse Training via Balancing the Exploration-Exploitation Trade-off
Shaoyi Huang, Bowen Lei, Dongkuan Xu +4
Over-parameterization of deep neural networks (DNNs) has shown high prediction accuracy for many applications. Although effective, the large number of parameters hinders its popula…
Aerial Manipulation Using a Novel Unmanned Aerial Vehicle Cyber-Physical System
Caiwu Ding, Hongwu Peng, Lu Lu +1
Unmanned Aerial Vehicles(UAVs) are attaining more and more maneuverability and sensory ability as a promising teleoperation platform for intelligent interaction with the environmen…
PolyMPCNet: Towards ReLU-free Neural Architecture Search in Two-party Computation Based Private Inference
Hongwu Peng, Shanglin Zhou, Yukui Luo +10
The rapid growth and deployment of deep learning (DL) has witnessed emerging privacy and security concerns. To mitigate these issues, secure multi-party computation (MPC) has been…
Towards Sparsification of Graph Neural Networks
Hongwu Peng, Deniz Gurevin, Shaoyi Huang +4
As real-world graphs expand in size, larger GNN models with billions of parameters are deployed. High parameter count in such models makes training and inference on graphs expensiv…
A Length Adaptive Algorithm-Hardware Co-design of Transformer on FPGA Through Sparse Attention and Dynamic Pipelining
Hongwu Peng, Shaoyi Huang, Shiyang Chen +8
Transformers are considered one of the most important deep learning models since 2018, in part because it establishes state-of-the-art (SOTA) records and could potentially replace…
An Automatic and Efficient BERT Pruning for Edge AI Systems
Shaoyi Huang, Ning Liu, Yueying Liang +5
With the yearning for deep learning democratization, there are increasing demands to implement Transformer-based natural language processing (NLP) models on resource-constrained de…