128 citations · 284 across the 7 of their papers we have counts for
7 papers
Achieving Cloud-Grade SLOs for Local Mixture-of-Experts Inference through CPU-GPU Hybrid Design
Wenxin Wang, Yule Hou, Yu Ji +2
Local deployment of large Mixture-of-Experts (MoE) models falls short of the service quality achieved in cloud-scale environments, even under low-concurrency workloads. We identify…
Neural Network Model Extraction Attacks in Edge Devices by Hearing Architectural Hints
Xing Hu, Ling Liang, Lei Deng +7
As neural networks continue their reach into nearly every aspect of software operations, the details of those networks become an increasingly sensitive subject. Even those that dep…
FPSA: A Full System Stack Solution for Reconfigurable ReRAM-based NN Accelerator Architecture
Yu Ji, Youyang Zhang, Xinfeng Xie +5
Neural Network (NN) accelerators with emerging ReRAM (resistive random access memory) technologies have been investigated as one of the promising solutions to address the \textit{m…
QGAN: Quantized Generative Adversarial Networks
Peiqi Wang, Dongsheng Wang, Yu Ji +5
The intensive computation and memory requirements of generative adversarial neural networks (GANs) hinder its real-world deployment on edge devices such as smartphones. Despite the…
Programmable Neural Network Trojan for Pre-Trained Feature Extractor
Yu Ji, Zixin Liu, Xing Hu +2
Neural network (NN) trojaning attack is an emerging and important attack model that can broadly damage the system deployed with NN models. Existing studies have explored the outsou…
Crossbar-aware neural network pruning
Ling Liang, Lei Deng, Yueling Zeng +5
Crossbar architecture based devices have been widely adopted in neural network accelerators by taking advantage of the high efficiency on vector-matrix multiplication (VMM) operati…
Bridging the Gap Between Neural Networks and Neuromorphic Hardware with A Neural Network Compiler
Yu Ji, YouHui Zhang, WenGuang Chen +1
Different from developing neural networks (NNs) for general-purpose processors, the development for NN chips usually faces with some hardware-specific restrictions, such as limited…