Xinkuang Geng

According to our database, Xinkuang Geng authored at least 7 papers between 2024 and 2025.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of five.

2025

A Low-Power Mixed-Precision Integrated Multiply-Accumulate Architecture for Quantized Deep Neural Networks.

Xiaolu Hu, Xinkuang Geng, Zhigang Mao, Jie Han, Honglan Jiang

Proceedings of the Design, Automation & Test in Europe Conference, 2025

Segment-Wise Accumulation: Low-Error Logarithmic Domain Computing for Efficient Large Language Model Inference.

Xinkuang Geng, Yunjie Lu, Hui Wang, Honglan Jiang

Proceedings of the Design, Automation & Test in Europe Conference, 2025

Lookup Table Refactoring: Towards Efficient Logarithmic Number System Addition for Large Language Models.

Xinkuang Geng, Siting Liu, Hui Wang, Jie Han, Honglan Jiang

Proceedings of the Design, Automation & Test in Europe Conference, 2025

2024

A Low-Power and High-Accuracy Approximate Adder for Logarithmic Number System.

Wenhui Zhang, Xinkuang Geng, Qin Wang, Jie Han, Honglan Jiang

Proceedings of the Great Lakes Symposium on VLSI 2024, 2024

A Configurable Approximate Multiplier for CNNs Using Partial Product Speculation.

Xiaolu Hu, Ao Liu, Xinkuang Geng, Zizhong Wei, Kai Jiang, Honglan Jiang

Proceedings of the Design, Automation & Test in Europe Conference & Exhibition, 2024

Compact Powers-of-Two: An Efficient Non-Uniform Quantization for Deep Neural Networks.

Xinkuang Geng, Siting Liu, Jianfei Jiang, Kai Jiang, Honglan Jiang

Proceedings of the Design, Automation & Test in Europe Conference & Exhibition, 2024

QUQ: Quadruplet Uniform Quantization for Efficient Vision Transformer Inference.

Xinkuang Geng, Siting Liu, Leibo Liu, Jie Han, Honglan Jiang

Proceedings of the 61st ACM/IEEE Design Automation Conference, 2024