About Me
Yupu Liang is a Ph.D. student in Chinese Information Processing Group (CIP), Institute of Automation, Chinese Academy of Sciences, advised by Yu Zhou and Chengqing Zong. Before that, he received his B.E. degree in School of Automation Science and Electrical Engineering at Beihang University in 2021. His research focuses on multimodal large language model, document AI, and machine translation.
News
[2024.04] π οΈ The DoTA dataset and code for DIMTDA have been released. [Github]
[2024.03] π Our new work Document Image Machine Translation with Dynamic Multi-pre-trained Models Assembling has been accepted by NAACL 2024 Main.
[2024.02] π Our new work Born a BabNet with Hierarchical Parental Supervision for End-to-End Text Image Machine Translation has been accepted by LREC-COLING 2024.
[2023.10] π Our new work LayoutDIT: Layout-Aware End-to-End Document Image Translation with Multi-Step Conductive Decoder has been accepted by EMNLP 2023 Findings.
Publications
- Yupu Liang, Yaping Zhang, Cong Ma, Zhiyang Zhang, Yang Zhao, Lu Xiang, Chengqing Zong, Yu Zhou. Document Image Machine Translation with Dynamic Multi-pre-trained Models Assembling. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL 2024). 2024. [ACL Anthology]
- Cong Ma, Yaping Zhang, Zhiyang Zhang, Yupu Liang, Yang Zhao, Yu Zhou, Chengqing Zong. Born a BabNet with Hierarchical Parental Supervision for End-to-End Text Image Machine Translation. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024). 2024. [ACL Anthology]
- Zhiyang Zhang, Yaping Zhang, Yupu Liang, Lu Xiang, Yang Zhao, Yu Zhou, Chengqing Zong. LayoutDIT: Layout-Aware End-to-End Document Image Translation with Multi-Step Conductive Decoder. In Findings of the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP 2023). 2023. [ACL Anthology]
- Bing Sun, Yi Xu, Shuhang Xie, Dong Xu, Yupu Liang. Data Processing Methods of Flow Field Based on Artificial Lateral Line Pressure Sensors. In the Journal of Bionic Engineering (JBE). 2022. [Springer]
Educations
[2021.09 - Now] Ph.D. Computer Science, Institute of Automation, Chinese Academy of Sciences
[2017.09 - 2021.06] Undergraduate. Automation, School of Automation Science and Electrical Engineering, Beihang University (National Scholarship, Outstanding Graduate of Beijing)
Moreβ¦
The profile is generated by Stable Diffusion.π