Pengxiang Xu

According to our database, Pengxiang Xu authored at least 17 papers between 2020 and 2026.

Collaborative distances:

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

2026

Calibrating and Rotating: A Unified Framework for Weight Conditioning in PEFT.

Da Chang, Peng Xue, Yu Li, Yongxiang Liu, Pengxiang Xu, Shixun Zhang

Proceedings of the Fortieth AAAI Conference on Artificial Intelligence, 2026

2025

SGEMM-cube: Emulating FP32 GEMM on Ascend NPUs Using FP16 Cube Units with Precision Recovery.

Weicheng Xue, Baisong Xu, Kai Yang, Yongxiang Liu, Dengdeng Fan, Pengxiang Xu, Yonghong Tian

CoRR, July, 2025

Efficient Low-Precision GEMM on Ascend NPU: HGEMM's Synergy of Pipeline Scheduling, Tiling, and Memory Optimization.

Erkun Zhang, Pengxiang Xu, Lu Lu

Comput., 2025

2024

Detecting facial manipulated images via one-class domain generalization.

Pengxiang Xu, Zhiyuan Ma, Xue Mei, Jie Shen

Multim. Syst., February, 2024

Uncertainty guided test-time training for face forgery detection.

Pengxiang Xu, Yang He, Jian Yang, Shanshan Zhang

Comput. Vis. Image Underst., 2024

Block Coordinate Descent Methods for Optimization under J-Orthogonality Constraints with Applications.

Di He, Ganzhao Yuan, Xiao Wang, Pengxiang Xu

CoRR, 2024

Unlocking High Performance with Low-Bit NPUs and CPUs for Highly Optimized HPL-MxP on Cloud Brain II.

Weicheng Xue, Kai Yang, Yongxiang Liu, Dengdong Fan, Pengxiang Xu, Yonghong Tian

Proceedings of the International Conference for High Performance Computing, 2024

Improving GPU Energy Efficiency through an Application-transparent Frequency Scaling Policy with Performance Assurance.

Yijia Zhang, Qiang Wang, Zhe Lin, Pengxiang Xu, Bingqiang Wang

Proceedings of the Nineteenth European Conference on Computer Systems, 2024

2023

An Efficient Fisher Matrix Approximation Method for Large-Scale Neural Network Optimization.

Minghan Yang, Dong Xu, Qiwen Cui, Zaiwen Wen, Pengxiang Xu

IEEE Trans. Pattern Anal. Mach. Intell., May, 2023

2022

Sketch-Based Empirical Natural Gradient Methods for Deep Learning.

Minghan Yang, Dong Xu, Zaiwen Wen, Mengyun Chen, Pengxiang Xu

J. Sci. Comput., 2022

Data fusing and joint training for learning with noisy labels.

Yi Wei, Mei Xue, Xin Liu, Pengxiang Xu

Frontiers Comput. Sci., 2022

2021

Simulating noisy variational quantum eigensolver with local noise models.

Jinfeng Zeng, Zipeng Wu, Chenfeng Cao, Chao Zhang, Shi-Yao Hou, Pengxiang Xu, Bei Zeng

Quantum Eng., 2021

Filtration network: A frame sampling strategy via deep reinforcement learning for video captioning.

Tiancheng Qian, Xue Mei, Pengxiang Xu, Kangqi Ge, Zhelei Qiu

J. Intell. Fuzzy Syst., 2021

NG+ : A Multi-Step Matrix-Product Natural Gradient Method for Deep Learning.

Minghan Yang, Dong Xu, Qiwen Cui, Zaiwen Wen, Pengxiang Xu

CoRR, 2021

DST: Data Selection and joint Training for Learning with Noisy Labels.

Yi Wei, Xue Mei, Xin Liu, Pengxiang Xu

CoRR, 2021

Robust Facial Manipulation Detection via Domain Generalization.

Pengxiang Xu, Xue Mei, Yi Wei, Tiancheng Qian

Proceedings of the ICCAI '21: 2021 7th International Conference on Computing and Artificial Intelligence, Tianjin China, April 23, 2021

2020

Simulating Noisy Quantum Circuits with Matrix Product Density Operators.

Song Cheng, Chenfeng Cao, Chao Zhang, Yongxiang Liu, Shi-Yao Hou, Pengxiang Xu, Bei Zeng

CoRR, 2020