Yanjun Ma - Academic Homepage

Biography

Yanjun Ma is a research scientist at Baidu. He received his BA and MA in Computational Linguistics from Shandong University and Tsinghua University in 2003 and 2006 respectively, and his PhD in Computer Science from Dublin City University in 2009.

He oversees the development of the open-source PaddlePaddle Deep Learning framework. His recent research interests include large language models and training and inference infrastructure. His previous research covers Natural Language Processing, with a particular focus on Machine Translation and Question Answering. He has authored and co-authored over 20 research publications in top-tier venues.

Publications

For a complete list, visit my Google Scholar profile.

PaddleOCR 3.0 Technical Report

C Cui, T Sun, M Lin, T Gao, Y Zhang, J Liu, X Wang, Z Zhang, C Zhou, et al.

arXiv preprint arXiv:2507.05595, 2025
PaddleOCR-VL: Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model

C Cui, T Sun, S Liang, T Gao, Z Zhang, J Liu, X Wang, et al.

arXiv preprint arXiv:2510.14528, 2025
HeterPS: Distributed Deep Learning with Reinforcement Learning Based Scheduling in Heterogeneous Environments

J Liu, Z Wu, D Feng, M Zhang, X Wu, X Yao, D Yu, Y Ma, F Zhao, D Dou

Future Generation Computer Systems 148, 106–117, 2023
PP-LiteSeg: A Superior Real-Time Semantic Segmentation Model

J Peng, Y Liu, S Tang, Y Hao, L Chu, G Chen, Z Wu, Z Chen, Z Yu, Y Du, et al.

arXiv preprint arXiv:2204.02681, 2022
SDWPF: A Dataset for Spatial Dynamic Wind Power Forecasting Challenge at KDD Cup 2022

J Zhou, X Lu, Y Xiao, J Su, J Lyu, Y Ma, D Dou

arXiv preprint arXiv:2208.04360, 2022
PP-LCNet: A Lightweight CPU Convolutional Neural Network

C Cui, T Gao, S Wei, Y Du, R Guo, S Dong, B Lu, Y Zhou, X Lv, Q Liu, et al.

arXiv preprint arXiv:2109.15099, 2021
Emerging Trends: A Gentle Introduction to Fine-Tuning

KW Church, Z Chen, Y Ma

Natural Language Engineering 27(6), 763–778, 2021
ERNIE 3.0 Titan: Exploring Larger-Scale Knowledge Enhanced Pre-Training for Language Understanding and Generation

S Wang, Y Sun, Y Xiang, Z Wu, S Ding, W Gong, S Feng, J Shang, Y Zhao, et al.

arXiv preprint arXiv:2112.12731, 2021
PP-OCRv2: Bag of Tricks for Ultra Lightweight OCR System

Y Du, C Li, R Guo, C Cui, W Liu, J Zhou, B Lu, Y Yang, Q Liu, X Hu, D Yu, et al.

arXiv preprint arXiv:2109.03144, 2021
PaddlePaddle: An Open-Source Deep Learning Platform from Industrial Practice

Y Ma, D Yu, T Wu, H Wang

Frontiers of Data and Computing 1(1), 105–115, 2019
Statistical Post-Editing for a Statistical MT System

H Béchara, Y Ma, J van Genabith

MT Summit XIII, 308–315, 2011
Consistent Translation Using Discriminative Learning: A Translation Memory-Inspired Approach

Y Ma, Y He, A Way

Proceedings of ACL 2011, Portland, OR
Bridging SMT and TM with Translation Recommendation

Y He, Y Ma, J van Genabith, A Way

Proceedings of ACL 2010, Uppsala, Sweden
TM-SMT Integration as Ranking

Y He, Y Ma, J van Genabith, A Way

Proceedings of COLING 2010, Beijing, China
Bilingually Motivated Word Segmentation for Statistical Machine Translation

Y Ma, A Way

ACM Transactions on Asian Language Information Processing 8(2), 2009
Bilingually Motivated Domain-Adapted Word Segmentation for Statistical Machine Translation

Y Ma, A Way

Proceedings of EACL 2009, Athens, Greece
Bootstrapping Word Alignment via Word Packing

Y Ma, A Way

Proceedings of ACL 2007, Prague, Czech Republic