Alert button
Picture for Cong Hao

Cong Hao

Alert button

INR-Arch: A Dataflow Architecture and Compiler for Arbitrary-Order Gradient Computations in Implicit Neural Representation Processing

Aug 11, 2023
Stefan Abi-Karam, Rishov Sarkar, Dejia Xu, Zhiwen Fan, Zhangyang Wang, Cong Hao

Figure 1 for INR-Arch: A Dataflow Architecture and Compiler for Arbitrary-Order Gradient Computations in Implicit Neural Representation Processing
Figure 2 for INR-Arch: A Dataflow Architecture and Compiler for Arbitrary-Order Gradient Computations in Implicit Neural Representation Processing
Figure 3 for INR-Arch: A Dataflow Architecture and Compiler for Arbitrary-Order Gradient Computations in Implicit Neural Representation Processing
Figure 4 for INR-Arch: A Dataflow Architecture and Compiler for Arbitrary-Order Gradient Computations in Implicit Neural Representation Processing
Viaarxiv icon

Rapid-INR: Storage Efficient CPU-free DNN Training Using Implicit Neural Representation

Jun 29, 2023
Hanqiu Chen, Hang Yang, Stephen BR Fitzmeyer, Cong Hao

Figure 1 for Rapid-INR: Storage Efficient CPU-free DNN Training Using Implicit Neural Representation
Figure 2 for Rapid-INR: Storage Efficient CPU-free DNN Training Using Implicit Neural Representation
Figure 3 for Rapid-INR: Storage Efficient CPU-free DNN Training Using Implicit Neural Representation
Figure 4 for Rapid-INR: Storage Efficient CPU-free DNN Training Using Implicit Neural Representation
Viaarxiv icon

Edge-MoE: Memory-Efficient Multi-Task Vision Transformer Architecture with Task-level Sparsity via Mixture-of-Experts

May 30, 2023
Rishov Sarkar, Hanxue Liang, Zhiwen Fan, Zhangyang Wang, Cong Hao

Figure 1 for Edge-MoE: Memory-Efficient Multi-Task Vision Transformer Architecture with Task-level Sparsity via Mixture-of-Experts
Figure 2 for Edge-MoE: Memory-Efficient Multi-Task Vision Transformer Architecture with Task-level Sparsity via Mixture-of-Experts
Figure 3 for Edge-MoE: Memory-Efficient Multi-Task Vision Transformer Architecture with Task-level Sparsity via Mixture-of-Experts
Figure 4 for Edge-MoE: Memory-Efficient Multi-Task Vision Transformer Architecture with Task-level Sparsity via Mixture-of-Experts
Viaarxiv icon

DGNN-Booster: A Generic FPGA Accelerator Framework For Dynamic Graph Neural Network Inference

Apr 13, 2023
Hanqiu Chen, Cong Hao

Figure 1 for DGNN-Booster: A Generic FPGA Accelerator Framework For Dynamic Graph Neural Network Inference
Figure 2 for DGNN-Booster: A Generic FPGA Accelerator Framework For Dynamic Graph Neural Network Inference
Figure 3 for DGNN-Booster: A Generic FPGA Accelerator Framework For Dynamic Graph Neural Network Inference
Figure 4 for DGNN-Booster: A Generic FPGA Accelerator Framework For Dynamic Graph Neural Network Inference
Viaarxiv icon

GNNBuilder: An Automated Framework for Generic Graph Neural Network Accelerator Generation, Simulation, and Optimization

Mar 29, 2023
Stefan Abi-Karam, Cong Hao

Figure 1 for GNNBuilder: An Automated Framework for Generic Graph Neural Network Accelerator Generation, Simulation, and Optimization
Figure 2 for GNNBuilder: An Automated Framework for Generic Graph Neural Network Accelerator Generation, Simulation, and Optimization
Figure 3 for GNNBuilder: An Automated Framework for Generic Graph Neural Network Accelerator Generation, Simulation, and Optimization
Figure 4 for GNNBuilder: An Automated Framework for Generic Graph Neural Network Accelerator Generation, Simulation, and Optimization
Viaarxiv icon

M$^3$ViT: Mixture-of-Experts Vision Transformer for Efficient Multi-task Learning with Model-Accelerator Co-design

Oct 26, 2022
Hanxue Liang, Zhiwen Fan, Rishov Sarkar, Ziyu Jiang, Tianlong Chen, Kai Zou, Yu Cheng, Cong Hao, Zhangyang Wang

Figure 1 for M$^3$ViT: Mixture-of-Experts Vision Transformer for Efficient Multi-task Learning with Model-Accelerator Co-design
Figure 2 for M$^3$ViT: Mixture-of-Experts Vision Transformer for Efficient Multi-task Learning with Model-Accelerator Co-design
Figure 3 for M$^3$ViT: Mixture-of-Experts Vision Transformer for Efficient Multi-task Learning with Model-Accelerator Co-design
Figure 4 for M$^3$ViT: Mixture-of-Experts Vision Transformer for Efficient Multi-task Learning with Model-Accelerator Co-design
Viaarxiv icon

Data-Model-Circuit Tri-Design for Ultra-Light Video Intelligence on Edge Devices

Oct 18, 2022
Yimeng Zhang, Akshay Karkal Kamath, Qiucheng Wu, Zhiwen Fan, Wuyang Chen, Zhangyang Wang, Shiyu Chang, Sijia Liu, Cong Hao

Figure 1 for Data-Model-Circuit Tri-Design for Ultra-Light Video Intelligence on Edge Devices
Figure 2 for Data-Model-Circuit Tri-Design for Ultra-Light Video Intelligence on Edge Devices
Figure 3 for Data-Model-Circuit Tri-Design for Ultra-Light Video Intelligence on Edge Devices
Figure 4 for Data-Model-Circuit Tri-Design for Ultra-Light Video Intelligence on Edge Devices
Viaarxiv icon

Bottleneck Analysis of Dynamic Graph Neural Network Inference on CPU and GPU

Oct 08, 2022
Hanqiu Chen, Yahya Alhinai, Yihan Jiang, Eunjee Na, Cong Hao

Figure 1 for Bottleneck Analysis of Dynamic Graph Neural Network Inference on CPU and GPU
Figure 2 for Bottleneck Analysis of Dynamic Graph Neural Network Inference on CPU and GPU
Figure 3 for Bottleneck Analysis of Dynamic Graph Neural Network Inference on CPU and GPU
Figure 4 for Bottleneck Analysis of Dynamic Graph Neural Network Inference on CPU and GPU
Viaarxiv icon

Unsupervised Learning for Combinatorial Optimization with Principled Objective Relaxation

Jul 14, 2022
Haoyu Wang, Nan Wu, Hang Yang, Cong Hao, Pan Li

Figure 1 for Unsupervised Learning for Combinatorial Optimization with Principled Objective Relaxation
Figure 2 for Unsupervised Learning for Combinatorial Optimization with Principled Objective Relaxation
Figure 3 for Unsupervised Learning for Combinatorial Optimization with Principled Objective Relaxation
Figure 4 for Unsupervised Learning for Combinatorial Optimization with Principled Objective Relaxation
Viaarxiv icon

RT-DNAS: Real-time Constrained Differentiable Neural Architecture Search for 3D Cardiac Cine MRI Segmentation

Jun 13, 2022
Qing Lu, Xiaowei Xu, Shunjie Dong, Cong Hao, Lei Yang, Cheng Zhuo, Yiyu Shi

Figure 1 for RT-DNAS: Real-time Constrained Differentiable Neural Architecture Search for 3D Cardiac Cine MRI Segmentation
Figure 2 for RT-DNAS: Real-time Constrained Differentiable Neural Architecture Search for 3D Cardiac Cine MRI Segmentation
Figure 3 for RT-DNAS: Real-time Constrained Differentiable Neural Architecture Search for 3D Cardiac Cine MRI Segmentation
Figure 4 for RT-DNAS: Real-time Constrained Differentiable Neural Architecture Search for 3D Cardiac Cine MRI Segmentation
Viaarxiv icon