I am a second-year PhD student in the Department of Computer Science at the University of Illinois Urbana-Champaign working on Natural Language Processing (NLP) with Professor Heng Ji.
I'm interested in building (multimodal) interactive agents (e.g., chatbots, robots) that can assist humans in both online and physical environments. Specifically, I am interested in building interactive language agents (e.g., Large Language Model) that can interact with environments through programming languages (e.g., Python) and learn from both automated and human language feedback.
Previously, I was an intern at Google Research NYC (2023), Microsoft (2022), Bytedance AI Lab (2021), and Tencent (2020). I received my undergraduate degree at the University of Michigan in computer science and data science, where I was fortunate to work with Professor David Jurgens, Daniel Romero, Rada Mihalcea, and Joyce Chai as a research assistant.
September 2023: Checkout our new preprint on evaluating LLMs in Multi-turn Interaction!
May 2023: Excited to share that I'll be joining Google Research NYC this
summer as a student researcher!
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.
* denotes equal contribution.
MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback
Xingyao Wang*, Zihan Wang*, Jiateng Liu, Yangyi Chen, Lifan Yuan, Hao Peng, Heng Ji
arxiv preprint.
Paper
Website
Code
CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsets
Lifan Yuan*, Yangyi Chen*, Xingyao Wang, Yi R. Fung, Hao Peng, Heng Ji
arxiv preprint.
Paper
Code
LETI: Learning to Generate from Textual Interactions
Xingyao Wang, Hao Peng, Reyhaneh Jabbarvand, Heng Ji
arxiv preprint.
Paper
Code
Twitter
Thread
Code4Struct: Code Generation for Few-Shot Structured Prediction from Natural Language
Xingyao Wang, Sha Li, Heng Ji
ACL 2023
Paper
Code
Poster
Twitter
Thread
POTATO: The Portable Text Annotation Tool
Jiaxin Pei, Aparna Ananthasubramaniam, Xingyao Wang, Naitian Zhou, Jackson Sargent, Apostolos
Dedeloudis, David Jurgens
EMNLP 2022 (demo)
Paper
Code
An Animated Picture Says at Least a Thousand Words: Selecting Gif-based Replies in Multimodal
Dialog
Xingyao Wang, David Jurgens
Findings of EMNLP 2021
Paper
Code
Presentation
video
Poster
Twitter
Thread
Imgur Post
Slack Gif
Bot
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
MLSys, 2021.
Paper
Student Researcher
Google Research
Summer 2023
New York, NY
Research Intern
Microsoft (Data & AI team @
Cloud and AI division)
Summer 2022
Instructional Aide
EECS 492: Introduction to Artificial Intelligence
Winter 2022
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
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
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.