Hongwu Peng
University of Connecticut
H-index: 15
North America-United States
Top articles of Hongwu Peng
MaxK-GNN: Extremely Fast GPU Kernel Design for Accelerating Graph Neural Networks Training
2024/4/27
Learning from Teaching Regularization: Generalizable Correlations Should be Easy to Imitate
arXiv preprint arXiv:2402.02769
2024/2/5
Zero-Space Cost Fault Tolerance for Transformer-based Language Models on ReRAM
arXiv preprint arXiv:2401.11664
2024/1/22
Medusa: Simple llm inference acceleration framework with multiple decoding heads
arXiv preprint arXiv:2401.10774
2024/1/19
Advanced language model-driven verilog development: Enhancing power, performance, and area optimization in code synthesis
arXiv preprint arXiv:2312.01022
2023/12/2
Hongwu Peng
H-Index: 5
Caiwen Ding
H-Index: 14
Evaluating Emerging AI/ML Accelerators: IPU, RDU, and NVIDIA/AMD GPUs
arXiv preprint arXiv:2311.04417
2023/11/8
Accel-gcn: High-performance gpu accelerator design for graph convolution networks
2023/10/28
AQ2PNN: Enabling Two-party Privacy-Preserving Deep Neural Network Inference with Adaptive Quantization
2023/10/28
Nuo Xu
H-Index: 5
Hongwu Peng
H-Index: 5
Chenghong Wang
H-Index: 5
Caiwen Ding
H-Index: 14
Xiaolin Xu
H-Index: 9
LinGCN: Structural Linearized Graph Convolutional Network for Homomorphically Encrypted Inference
2023/9/25
Dynamic sparse training via balancing the exploration-exploitation trade-off
2023/7/9
Pasnet: Polynomial architecture search framework for two-party computation-based secure neural network deployment
2023/7/9
Hongwu Peng
H-Index: 5
Nuo Xu
H-Index: 5
Chenghong Wang
H-Index: 5
Xiaolin Xu
H-Index: 9
Caiwen Ding
H-Index: 14
RRNet: Towards ReLU-Reduced Neural Network for Two-party Computation Based Private Inference
arXiv preprint arXiv:2302.02292
2023/2/5
Hongwu Peng
H-Index: 5
Nuo Xu
H-Index: 5
Chenghong Wang
H-Index: 5
Xiaolin Xu
H-Index: 9
Caiwen Ding
H-Index: 14
Design and validation of a MVDC isolated active voltage injection based HCB
IEEE Transactions on Industry Applications
2023/1/31
Autorep: Automatic relu replacement for fast private network inference
2023
Codg-reram: An algorithm-hardware co-design to accelerate semi-structured gnns on reram
2022/10/23
Towards sparsification of graph neural networks
2022/9/11
Si-IGBT and SiC-MOSFET hybrid switch-based 1.7 kV half-bridge power module
Power Electronic Devices and Components
2022/10/1
A length adaptive algorithm-hardware co-design of transformer on fpga through sparse attention and dynamic pipelining
2022/7/10
An automatic and efficient BERT pruning for edge AI systems
2022/4/6
Ning Liu
H-Index: 6
Hongwu Peng
H-Index: 5
Hongjia Li
H-Index: 7
Dongkuan Xu
H-Index: 6
Caiwen Ding
H-Index: 14
Performance comparison and modelling of instantaneous current sharing amongst gan hemt switch configurations for current source inverters
2022/3/20
Co-Authors
