Канал: BUAA-CI-Lab

Towards Efficient SRAM-PIM Architecture Design by Exploiting Unstructured Bit-Level Sparsity

Towards Efficient SRAM-PIM Architecture Design by Exploiting Unstructured Bit-Level Sparsity

Graph Neural Networks Automated Design and Deployment on Device-Edge Co-Inference Systems

Graph Neural Networks Automated Design and Deployment on Device-Edge Co-Inference Systems

GNNavigator: Towards Adaptive Training of Graph Neural Networks via Automatic Guideline Exploration

GNNavigator: Towards Adaptive Training of Graph Neural Networks via Automatic Guideline Exploration

Hardware-Aware Graph Neural Network Automated Designfor Edge Computing Platforms

Hardware-Aware Graph Neural Network Automated Designfor Edge Computing Platforms

Eventor: An Efficient Event-Based Monocular Multi-View Stereo Accelerator on FPGA Platform

Eventor: An Efficient Event-Based Monocular Multi-View Stereo Accelerator on FPGA Platform

Optimizing Memory Efficiency of Graph Neural Networks on Edge Computing Platforms

Optimizing Memory Efficiency of Graph Neural Networks on Edge Computing Platforms

Towards Systems Education for Artificial Intelligence: A Course Practice in Intelligent Computing ..

Towards Systems Education for Artificial Intelligence: A Course Practice in Intelligent Computing ..

FedSkel: Efficient Federated Learning on Heterogeneous Systems with Skeleton Gradients Update

FedSkel: Efficient Federated Learning on Heterogeneous Systems with Skeleton Gradients Update

TCIM: Triangle Counting Acceleration With Processing-In-MRAM Architecture

TCIM: Triangle Counting Acceleration With Processing-In-MRAM Architecture

SparseTrain: Exploiting Dataflow Sparsity for Efficient Convolutional Neural Networks Training

SparseTrain: Exploiting Dataflow Sparsity for Efficient Convolutional Neural Networks Training

Accelerating CNN Training by Pruning Activation Gradients

Accelerating CNN Training by Pruning Activation Gradients