Haikuo Shao

20 papers A 1C 3Journal 13Unranked 3
YearRankTypeTitle / Venue / Authors
2026 J jnl
APT-LLM: Exploiting Arbitrary-Precision Tensor Core Computing for LLM Acceleration.
IEEE Trans. Comput. Aided Des. Integr. Circuits Syst.
Shaobo Ma, Chao Fang, Haikuo Shao, Zhongfeng Wang
2025 J jnl
APT-LLM: Exploiting Arbitrary-Precision Tensor Core Computing for LLM Acceleration.
CoRR
Shaobo Ma, Chao Fang, Haikuo Shao, Zhongfeng Wang
2025 J jnl
ASTRA: Reconfigurable Training Architecture Design for Nonlinear Softmax and Activation Functions in Transformers.
IEEE Trans. Very Large Scale Integr. Syst.
Haikuo Shao, Zhongfeng Wang
2025 J jnl
AccLLM: Accelerating Long-Context LLM Inference Via Algorithm-Hardware Co-Design.
CoRR
Yanbiao Liang, Huihong Shi, Haikuo Shao, Zhongfeng Wang
2025 J jnl
An Efficient Layer Normalization Training Module With Dynamic Quantization for Transformers.
IEEE Trans. Circuits Syst. II Express Briefs
Haikuo Shao, Aotao Wang, Zhongfeng Wang
2025 C conf
An Efficient Training Architecture for Nonlinear Softmax Function in Transformers.
ISCAS
Haikuo Shao, Zhongfeng Wang
2025 — conf
Efficient Arbitrary Precision Acceleration for Large Language Models on GPU Tensor Cores.
ASP-DAC
Shaobo Ma, Chao Fang, Haikuo Shao, Zhongfeng Wang
2025 — conf
FastMamba: A High-Speed and Efficient Mamba Accelerator on FPGA with Accurate Quantization.
ISVLSI
Aotao Wang, Haikuo Shao, Shaobo Ma, Zhongfeng Wang
2025 J jnl
FastMamba: A High-Speed and Efficient Mamba Accelerator on FPGA with Accurate Quantization.
CoRR
Aotao Wang, Haikuo Shao, Shaobo Ma, Zhongfeng Wang
2025 J jnl
Trio-ViT: Post-Training Quantization and Acceleration for Softmax-Free Efficient Vision Transformer.
IEEE Trans. Circuits Syst. I Regul. Pap.
Huihong Shi, Haikuo Shao, Wendong Mao, Zhongfeng Wang
2024 C conf
A Flexible FPGA-Based Accelerator for Efficient Inference of Multi-Precision CNNs.
ISCAS
Xinyan Liu, Xiao Wu, Haikuo Shao, Zhongfeng Wang
2024 J jnl
A Low Complexity Online Learning Approximate Message Passing Detector for Massive MIMO.
IEEE Trans. Very Large Scale Integr. Syst.
Baoling Hong, Haikuo Shao, Zhongfeng Wang
2024 C conf
An FPGA-Based Reconfigurable Accelerator for Convolution-Transformer Hybrid EfficientViT.
ISCAS
Haikuo Shao, Huihong Shi, Wendong Mao, Zhongfeng Wang
2024 J jnl
An FPGA-Based Reconfigurable Accelerator for Convolution-Transformer Hybrid EfficientViT.
CoRR
Haikuo Shao, Huihong Shi, Wendong Mao, Zhongfeng Wang
2024 A conf
Co-Designing Binarized Transformer and Hardware Accelerator for Efficient End-to-End Edge Deployment.
ICCAD
Yuhao Ji, Chao Fang, Shaobo Ma, Haikuo Shao, Zhongfeng Wang
2024 J jnl
Co-Designing Binarized Transformer and Hardware Accelerator for Efficient End-to-End Edge Deployment.
CoRR
Yuhao Ji, Chao Fang, Shaobo Ma, Haikuo Shao, Zhongfeng Wang
2024 J jnl
Efficient Arbitrary Precision Acceleration for Large Language Models on GPU Tensor Cores.
CoRR
Shaobo Ma, Chao Fang, Haikuo Shao, Zhongfeng Wang
2024 J jnl
Trio-ViT: Post-Training Quantization and Acceleration for Softmax-Free Efficient Vision Transformer.
CoRR
Huihong Shi, Haikuo Shao, Wendong Mao, Zhongfeng Wang
2023 J jnl
An Efficient Training Accelerator for Transformers With Hardware-Algorithm Co-Optimization.
IEEE Trans. Very Large Scale Integr. Syst.
Haikuo Shao, Jinming Lu, Meiqi Wang, Zhongfeng Wang
2021 — conf
An FPGA-Based Reconfigurable Accelerator for Low-Bit DNN Training.
ISVLSI
Haikuo Shao, Jinming Lu, Jun Lin, Zhongfeng Wang