Picture for Sitao Huang

Sitao Huang

TG-NAS: Leveraging Zero-Cost Proxies with Transformer and Graph Convolution Networks for Efficient Neural Architecture Search

Mar 30, 2024
Viaarxiv icon

MicroNAS: Zero-Shot Neural Architecture Search for MCUs

Jan 17, 2024
Viaarxiv icon

CARMA: Context-Aware Runtime Reconfiguration for Energy-Efficient Sensor Fusion

Jun 27, 2023
Figure 1 for CARMA: Context-Aware Runtime Reconfiguration for Energy-Efficient Sensor Fusion
Figure 2 for CARMA: Context-Aware Runtime Reconfiguration for Energy-Efficient Sensor Fusion
Figure 3 for CARMA: Context-Aware Runtime Reconfiguration for Energy-Efficient Sensor Fusion
Figure 4 for CARMA: Context-Aware Runtime Reconfiguration for Energy-Efficient Sensor Fusion
Viaarxiv icon

Late Breaking Results: Scalable and Efficient Hyperdimensional Computing for Network Intrusion Detection

Apr 11, 2023
Figure 1 for Late Breaking Results: Scalable and Efficient Hyperdimensional Computing for Network Intrusion Detection
Figure 2 for Late Breaking Results: Scalable and Efficient Hyperdimensional Computing for Network Intrusion Detection
Figure 3 for Late Breaking Results: Scalable and Efficient Hyperdimensional Computing for Network Intrusion Detection
Figure 4 for Late Breaking Results: Scalable and Efficient Hyperdimensional Computing for Network Intrusion Detection
Viaarxiv icon

DistHD: A Learner-Aware Dynamic Encoding Method for Hyperdimensional Classification

Add code
Apr 11, 2023
Figure 1 for DistHD: A Learner-Aware Dynamic Encoding Method for Hyperdimensional Classification
Figure 2 for DistHD: A Learner-Aware Dynamic Encoding Method for Hyperdimensional Classification
Figure 3 for DistHD: A Learner-Aware Dynamic Encoding Method for Hyperdimensional Classification
Figure 4 for DistHD: A Learner-Aware Dynamic Encoding Method for Hyperdimensional Classification
Viaarxiv icon

PIGEON: Optimizing CUDA Code Generator for End-to-End Training and Inference of Relational Graph Neural Networks

Jan 16, 2023
Figure 1 for PIGEON: Optimizing CUDA Code Generator for End-to-End Training and Inference of Relational Graph Neural Networks
Figure 2 for PIGEON: Optimizing CUDA Code Generator for End-to-End Training and Inference of Relational Graph Neural Networks
Figure 3 for PIGEON: Optimizing CUDA Code Generator for End-to-End Training and Inference of Relational Graph Neural Networks
Figure 4 for PIGEON: Optimizing CUDA Code Generator for End-to-End Training and Inference of Relational Graph Neural Networks
Viaarxiv icon

Chimera: A Hybrid Machine Learning Driven Multi-Objective Design Space Exploration Tool for FPGA High-Level Synthesis

Jul 03, 2022
Viaarxiv icon

Efficient Machine Learning, Compilers, and Optimizations for Embedded Systems

Jun 06, 2022
Figure 1 for Efficient Machine Learning, Compilers, and Optimizations for Embedded Systems
Figure 2 for Efficient Machine Learning, Compilers, and Optimizations for Embedded Systems
Figure 3 for Efficient Machine Learning, Compilers, and Optimizations for Embedded Systems
Figure 4 for Efficient Machine Learning, Compilers, and Optimizations for Embedded Systems
Viaarxiv icon

Large Graph Convolutional Network Training with GPU-Oriented Data Communication Architecture

Add code
Mar 04, 2021
Figure 1 for Large Graph Convolutional Network Training with GPU-Oriented Data Communication Architecture
Figure 2 for Large Graph Convolutional Network Training with GPU-Oriented Data Communication Architecture
Figure 3 for Large Graph Convolutional Network Training with GPU-Oriented Data Communication Architecture
Figure 4 for Large Graph Convolutional Network Training with GPU-Oriented Data Communication Architecture
Viaarxiv icon

Mind Mappings: Enabling Efficient Algorithm-Accelerator Mapping Space Search

Add code
Mar 02, 2021
Figure 1 for Mind Mappings: Enabling Efficient Algorithm-Accelerator Mapping Space Search
Viaarxiv icon