Seguir
Yuhui Xu
Yuhui Xu
Research Scientist, Salesforce AI Research Asia
Dirección de correo verificada de salesforce.com - Página principal
Título
Citado por
Citado por
Año
PC-DARTS: Partial Channel Connections for Memory-Efficient Architecture Search
Y Xu, L Xie, X Zhang, X Chen, GJ Qi, Q Tian, H Xiong
International Conference on Learning Representations, 2020
7492020
Deep neural network compression with single and multiple level quantization
Y Xu, Y Wang, A Zhou, W Lin, H Xiong
Proceedings of the AAAI conference on artificial intelligence 32 (1), 2018
1352018
Weight-sharing neural architecture search: A battle to shrink the optimization gap
L Xie, X Chen, K Bi, L Wei, Y Xu, L Wang, Z Chen, A Xiao, J Chang, ...
ACM Computing Surveys (CSUR) 54 (9), 1-37, 2021
802021
Trp: Trained rank pruning for efficient deep neural networks
Y Xu, Y Li, S Zhang, W Wen, B Wang, Y Qi, Y Chen, W Lin, H Xiong
arXiv preprint arXiv:2004.14566, 2020
712020
Partially-connected neural architecture search for reduced computational redundancy
Y Xu, L Xie, W Dai, X Zhang, X Chen, GJ Qi, H Xiong, Q Tian
IEEE Transactions on Pattern Analysis and Machine Intelligence 43 (9), 2953-2970, 2021
522021
Trained rank pruning for efficient deep neural networks
Y Xu, Y Li, S Zhang, W Wen, B Wang, W Dai, Y Qi, Y Chen, W Lin, ...
2019 Fifth Workshop on Energy Efficient Machine Learning and Cognitive …, 2019
492019
Latency-aware differentiable neural architecture search
Y Xu, L Xie, X Zhang, X Chen, B Shi, Q Tian, H Xiong
arXiv preprint arXiv:2001.06392, 2020
382020
Filter level pruning based on similar feature extraction for convolutional neural networks
L Li, Y Xu, J Zhu
IEICE TRANSACTIONS on Information and Systems 101 (4), 1203-1206, 2018
242018
Qa-lora: Quantization-aware low-rank adaptation of large language models
Y Xu, L Xie, X Gu, X Chen, H Chang, H Zhang, Z Chen, X Zhang, Q Tian
arXiv preprint arXiv:2309.14717, 2023
192023
Fitting the search space of weight-sharing nas with graph convolutional networks
X Chen, L Xie, J Wu, L Wei, Y Xu, Q Tian
Proceedings of the AAAI Conference on Artificial Intelligence 35 (8), 7064-7072, 2021
192021
Iterative deep neural network quantization with lipschitz constraint
Y Xu, W Dai, Y Qi, J Zou, H Xiong
IEEE Transactions on Multimedia 22 (7), 1874-1888, 2019
182019
DNQ: Dynamic Network Quantization
Y Xu, S Zhang, Y Qi, J Guo, W Lin, H Xiong
Data Compression Conference (DCC2019), 2018
102018
Dynamic-stride-net: Deep convolutional neural network with dynamic stride
Z Yang, Y Xu, W Dai, H Xiong
Optoelectronic Imaging and Multimedia Technology VI 11187, 42-53, 2019
72019
Bnet: Batch normalization with enhanced linear transformation
Y Xu, L Xie, C Xie, W Dai, J Mei, S Qiao, W Shen, H Xiong, A Yuille
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023
6*2023
Fedexg: Federated learning with model exchange
Z Mao, W Dai, C Li, Y Xu, S Wang, J Zou, H Xiong
2020 IEEE International Symposium on Circuits and Systems (ISCAS), 1-5, 2020
62020
Tiny-hourglassnet: An efficient design for 3d human pose estimation
B Shi, Y Xu, W Dai, B Wang, S Zhang, C Li, J Zou, H Xiong
2020 IEEE international conference on image processing (ICIP), 1491-1495, 2020
42020
Noise-to-Compression Variational Autoencoder for Efficient End-to-End Optimized Image Coding
J Luo, S Li, W Dai, Y Xu, D Cheng, G Li, H Xiong
2020 Data Compression Conference (DCC), 33-42, 2020
22020
Feature map alignment: Towards efficient design of mixed-precision quantization scheme
Y Bao, Y Xu, H Xiong
2019 IEEE Visual Communications and Image Processing (VCIP), 1-4, 2019
12019
Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models
X Lu, Q Liu, Y Xu, A Zhou, S Huang, B Zhang, J Yan, H Li
arXiv preprint arXiv:2402.14800, 2024
2024
El sistema no puede realizar la operación en estos momentos. Inténtalo de nuevo más tarde.
Artículos 1–19