Clicky



Hello there.


I am a senior at the University of Michigan studying computer science and data science. I am fortunate to work with Professor David Jurgens, Daniel Romero, Rada Mihalcea, and Joyce Chai as a research assistant.

I'm broadly interested in researching language technologies to build interactive multimodal language agents (e.g., chatbots and robots) that are socially-aware, able to assist humans across tasks and environments, including those deployed online or grounded to physical environments.

Particularly, I am interested in leveraging multimodal information to explore areas such as Interactive (dialog) Systems, Language Grounding, and Computational Social Science.

Previously, I was a natural language processing intern at Bytedance AI Lab and a software engineering intern at Tencent.

I am currently applying to PhD programs for Fall 2022.





Xingyao Wang (王星尧)
How to pronounce?
Pronouns: He/Him
Email: xingyaow@umich.edu

[Resume] [Google Scholar] [Github] [Linkedin] [Instagram]

Recent News

December 2021: I'm pleased to receive honorable mention for the Outstanding Undergraduate Researcher Awards!
October 2021: I'm honored to receive the EMNLP 2021 Student Travel Award! I will also be a Student Volunteer at EMNLP 2021, See y'all in Punta Cana!
August 2021: One paper is accepted to the Findings of EMNLP 2021 on building a gif-based dialog system! You can even install this bot to your Slack channel following instruction here.





Publications and Manuscripts.


An Animated Picture Says at Least a Thousand Words: Selecting Gif-based Replies in Multimodal Dialog
Xingyao Wang, David Jurgens
Proceedings of the Findings of the 2021 Conference on Empirical Methods in Natural Language Processing (Findings of EMNLP).
Paper Code Presentation video Poster Twitter Thread Imgur Post Slack Gif Bot Add to Slack


@inproceedings{
  author = {Wang, Xingyao and Jurgens, David},
  year = 2021,
  title = {{An Animated Picture Says at Least a Thousand Words: Selecting Gif-based Replies in Multimodal Dialog}},
  booktitle = {Proceedings of the Findings of the 2021 Conference on Empirical Methods in Natural Language Processing (Findings of EMNLP)}
}  
                

Towards Scalable Distributed Training of Deep Learning on Public Cloud Clusters
Shaohuai Shi*, Xianhao Zhou*, Shutao Song*, Xingyao Wang, Zilin Zhu, Xue Huang, Xinan Jiang, Feihu Zhou, Zhenyu Guo, Liqiang Xie, Rui Lan, Xianbin Ouyang, Yan Zhang, Jieqian Wei, Jing Gong, Weiliang Lin, Ping Gao, Peng Meng, Xiaomin Xu, Chenyang Guo, Bo Yang, Zhibo Chen, Yongjian Wu, Xiaowen Chu
Proceedings of Machine Learning and Systems (MLSys), 2021.
Paper


@inproceedings{MLSYS2021_8613985e,
  author = {Shi, Shaohuai and Zhou, Xianhao and Song, Shutao and Wang, Xingyao and Zhu, Zilin and Huang, Xue and Jiang, Xinan and Zhou, Feihu and Guo, Zhenyu and Xie, Liqiang and Lan, Rui and Ouyang, Xianbin and Zhang, Yan and Wei, Jieqian and Gong, Jing and  Lin, Weiliang and Gao, Ping and Meng, Peng and Xu, Xiaomin and Guo, Chenyang and Yang, Bo and Chen, Zhibo and Wu, Yongjian and Chu, Xiaowen},
  booktitle = {Proceedings of Machine Learning and Systems},
  editor = {A. Smola and A. Dimakis and I. Stoica},
  pages = {401--412},
  title = {Towards Scalable Distributed Training of Deep Learning on Public Cloud Clusters},
  url = {https://proceedings.mlsys.org/paper/2021/file/8613985ec49eb8f757ae6439e879bb2a-Paper.pdf},
  volume = {3},
  year = {2021}
  }               
                

Lane Extraction and Quality Evaluation: A Hough Transform Based Approach
Xingyao Wang, Da Yan, Ke Chen, Yancong Deng, Cheng Long, Kunlin Zhang, Sibo Yan
Proceedings of IEEE Conference on Multimedia Information Processing and Retrieval (MIPR), 2020.
Paper Code


@INPROCEEDINGS{9175569,  
  author={Wang, Xingyao and Yan, Da and Chen, Ke and Deng, Yancong and Long, Cheng and Zhang, Kunlin and Yan, Sibo},
  booktitle={2020 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR)},
  title={Lane Extraction and Quality Evaluation: A Hough Transform Based Approach},
  year={2020},
  volume={},
  number={},
  pages={7-12},
  doi={10.1109/MIPR49039.2020.00010}
}
                

Impact of Cross Community Exposure on Early Community Growth
Justin Huang, Tiago Cunha, Xingyao Wang, David Jurgens, Daniel Romero
Manuscript in Preparation.

Fake it til you make it: A large-scale field experiment in bootstrapping new communities through ecosystem-sourced content
Tiago Cunha*, Xingyao Wang*, Xingyu Lu, Justin Huang, David Jurgens, Daniel Romero
Manuscript in Preparation.

* Denotes equal contribution.




Experience.


Instructional Aide
EECS 492: Introduction to Artificial Intelligence
Winter 2022—Present
University of Michigan—Ann Arbor, MI

Undergraduate Researcher
Blablablab
Fall 2019—Present
University of Michigan—Ann Arbor, MI

Undergraduate Researcher
SLED
Fall 2021—Present
University of Michigan—Ann Arbor, MI

Undergraduate Researcher
LIT
Fall 2021—Present
University of Michigan—Ann Arbor, MI

Natural Language Processing Intern
ByteDance AI Lab (Lightseq)
Summer 2021
Beijing, China

Software Engineering Intern
Tencent (High-performance Deep Learning)
Summer 2020
Shenzhen, Guangdong, China


Selected Honors & Awards.


Honorable Mention, Computing Research Association Outstanding Undergraduate Researcher Award, 2022

EMNLP Student Travel Award (5 out of 94), 2021

James B. Angell Scholar, University of Michigan, 2021

University Honors, University of Michigan, 2017—2021

Peiyang Chunhui Scholarship, Tianjin University, 2018



Selected Relevant Coursework.


Natural Language Processing, Information Retrieval, Machine Learning, Theoretical Statistics, Web System, Artificial Intelligence, Probability, Data Structure and Algorithms, Computer Organization, Operating System.



Many thanks to Sky Wang for the site template.