Xiaoze Jiang

NLP Engineer

Kwai Inc. (Kwai)
Shangdixi Road No. 6, Haidian District, Beijing, China

Email / CV / Google Scholar / GitHub

About Me

I'm a NLP engineer in Kwai Inc. I got my Master Degree at School of Automation Science and Electrical Engineering (SASEE), Beihang University (BUAA), supervised by Prof. Zengchang Qin. I'm lucky to have opportunities to collaborate with Jing Yu (Professor at Chinese Academy of Sciences), Qi Wu (Professor at Adelaide), Yaobo Liang (Researcher at MSRA), Xingxing Zhang (Researcher at MSRA). Before this, I got my Bachelor's degree in Automation Science from Northeast Forestry University (2014-2018).

My primary research interests are Multi-modal Machine Learning and Natural Language Processing. Specifically, my current research focuses on vision and language, e.g. visual dialog, cross-lingual pre-training and image/video captioning.

News

[2021-12-01] 1 paper accepted by AAAI 2022!

[2021-11-04] We achieve the top of the CLUE 1.1 Classification Task List. [News1] [News2]

[2020-10-09] 1 paper accepted as accepted by IEEE Transactions on Image Processing (Impact factor: 9.34).

[2020-07-26] 1 paper accepted as oral paper by ACM MM 2020.

[2020-04-20] 1 paper accepted by IJCAI 2020.

[2019-12-22] I gave an invited talk about my accepted paper in AAAI 2020 in Peking University, Beijing, China. [Slide]

[2019-11-11] 1 paper accepted by AAAI 2020.

Education

	Beihang University Sep. 2018 -- Jan. 2021 M.S. candidate in Pattern Recognition Advisors: Prof. Zengchang Qin
	Northeast Forestry University Sep. 2014 -- Jun. 2018 BEng in Automation Science

Publications

	XLM-K: Improving Cross-Lingual Language Model Pre-Training with Multilingual Knowledge Xiaoze Jiang, Yaobo Liang, Weizhu Chen & Nan Duan AAAI 2022 (Accept rate: 1349/9251 = 15%) PDF / bibtex @inproceedings{jiang2022xlmk, title={XLM-K: Improving Cross-Lingual Language Model Pre-Training with Multilingual Knowle}, author={Jiang, Xiaoze and Liang, Yaobo and Chen, Weizhu and Duan, Nan}, booktitle={Thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI)}, year={2022} }
	Learning Dual Encoding Model for Adaptive Visual Understanding in Visual Dialogue Jing Yu, Xiaoze Jiang, Zengchang Qin, Weifeng Zhang, Yue Hu & Qi Wu IEEE Transactions on Image Processing (Impact factor: 9.34) PDF / bibtex @article{jiang2020learning, title={Learning Dual Encoding Model for Adaptive Visual Understanding in Visual Dialogue}, author={Yu, Jing and Jiang, Xiaoze and Qin, Zengchang and Zhang, Weifeng and Hu, Yue and Wu, Qi}, booktitle={IEEE Transactions on Image Processing}, year={2021}, volume={30}, pages={220-233}, doi={10.1109/TIP.2020.3034494} }
	KBGN: Knowledge-Bridge Graph Network for Adaptive Vision-Text Reasoning in Visual Dialogue Xiaoze Jiang, Siyi Du, Zengchang Qin, Yajing Sun & Jing Yu ACM MM 2020, Oral paper (Accept rate: 427/1698 = 27.8%, Oral rate: 151/1698 = 8.9%) PDF / bibtex @inproceedings{jiang2020kbgn, title={KBGN: Knowledge-Bridge Graph Network for Adaptive Vision-Text Reasoning in Visual Dialogue}, author={Jiang, Xiaoze and Du, Siyi and Qin, Zengchang Qin and Sun, Yajing and Yu, Jing}, booktitle={ACM Multimedia (ACM MM)}, pages={1265--1273} year={2020} }
	DAM: Deliberation, Abandon and Memory Networks for Generating Detailed and Non-repetitive Responses in Visual Dialogue Xiaoze Jiang, Jing Yu, Yajing Sun, Zengchang Qin, Zihao Zhu, Yue Hu & Qi Wu IJCAI 2020 (Accept rate: 592/4717 = 12.6%) PDF / bibtex @inproceedings{jiang2020dam, title={DAM: Deliberation, Abandon and Memory Networks for Generating Detailed and Non-repetitive Responses in Visual Dialogue}, author={Jiang, Xiaoze and Yu, Jing and Sun, Yajing and Qin, Zengchang and Zhu, Zihao and Hu, Yue and Wu, Qi}, booktitle={International Joint Conference on Artificial Intelligence (IJCAI)}, pages={687--693} year={2020} }
	DualVD: An Adaptive Dual Encoding Model for Deep Visual Understanding in Visual Dialogue Xiaoze Jiang, Jing Yu, Zengchang Qin, Yingying Zhuang, Xingxing Zhang, Yue Hu & Qi Wu AAAI 2020 (Accept rate: 1591/7737 = 20.6%) PDF / bibtex @inproceedings{jiang2020dualvd, title={DualVD: An Adaptive Dual Encoding Model for Deep Visual Understanding in Visual Dialogue}, author={Jiang, Xiaoze and Yu, Jing and Qin, Zengchang and Zhuang, Yingying and Zhang, Xingxing and Hu, Yue and Wu, Qi}, booktitle={Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI)}, pages={11125--11132}, year={2020} }

Internship

Microsoft Asia-Pacific Research and Development Group Internship 2020.04-2021.01

I'm working with Yaobo Liang (Researcher at MSRA) at MSRA.
Research direction: cross-lingual pre-training.

Chinese Academy of Sciences (CAS) Internship 2018.10-2020.03

I'm working with Jing Yu (Professor at Chinese Academy of Sciences) at Institute of Information Engineering.
Research direction: multi-modal machine learning, e.g. visual dialog.

HUAWEI TECHNOLOGIES CO.LTD. Internship 2019.06-2019.08

I'm working with Wenxiang Shi at HUAWEI.
Content: Responsible for the research of query-document matching for search system.

Contest

Visual Dialog Challenge, 2019 Top 6 Awards (6/37)

Mathematical Contest In Modeling of Northeastern Province, 2017 First Prize

Mathematical Contest In Modeling, 2017 Honorable Mention

National Mathematical Contest In Modeling, 2016 Second Prize

Selected Honors

Outstanding Graduate 2019

First-class Academic Scholarship 2019

National Scholarship 2017

Provincial-level Merit Student 2017

Website template from here.