With the goal of aligning AI and human values, my research strives to empower humans to interactively explain, evaluate, collaborate with AI, and further provide human feedback to enhance AI development. From a comprehensive view of Bidirectional Humans↔AI Alignment (systematic review of 400+ papers).
From a human-centered perspective, my research enhances the explainability and usability of deployed AI systems through interaction, enabling humans to better understand and collaborate with AI (e.g., ConvXAI (CSCW'23 Best Demo), HypoCompass (AIED'24 Best Paper)).
From an AI-centered perspective, my research aims to integrate human feedback into AI, by developing approaches to measure human values and incorporating them into AI development and customization (e.g., MultiTurnCleanup (EMNLP'23, Google Research Scholarship), Speaker Fairness (ICASSP'22, Amazon Alexa AI)).
My research is rooted in HCI and intersects with various AI fields, including NLP, speech, computer vision, and data science.
I use mixed research methods, such as quantitative and qualitative human studies and AI algorithm & interaction design, to foster bidirectional alignment comprehensively.
🌟
I'm on the academic & industry job market! Happy to connect with professors and researchers!
😊
If you're interested in working together with me, feel free to reach out — I'd love to chat!
BIO:
I am a postdoctoral scholar at the
Information School and the
RAISE Center at the
University of Washington, where I focus on
Bidirectional Human-AI Alignment research and closely work with Prof.
Tanu Mitra who co-founded the center.
I completed my Ph.D. at
College of IST at
Penn State from 2019.09 to 2023.07, where I am fortunately advised by Prof.
Ting-hao 'Kenneth' Huang, and committee: Profs.
Mary Beth Rosson,
C. Lee Giles,
S. Shyam Sundar (Penn State), Prof.
Sherry Tongshuang Wu (CMU), and my external mentor Dr.
Andreas Stolcke (Distinguished AI Scientist at Uniphore).
Additionally, I conducted research on speech processing and conversational AI during my internships at
Google Research and
Amazon Alexa AI.
Before UW, I spent one wonderful year as a postdoctoral research follow at
University of Michigan—Ann Arbor jointly affiliated with
UMSI and
CSE, working with
Prof. David Jurgens and many other amazing professors and students.
I am also deeply grateful for my collaborators, whose constructive insights greatly enriched my knowledge and expertise 🧡!
NEWS
Dec-2024 Our ICLR 2025 BiAlign Workshop has been officially accepted. Look forward to seeing more alignment studies and talks at our workshop!
Nov-2024 Giving talks on Bidirectional Alignment at Ph.D. seminars of Information Science at Cornell University, HCI seminars at Columbia University, and Northeastern University, excited to see you and talk with you!
Nov-2024 Gave a talk about Human-centered Alignment in Spoken LMs at Google DeepMind Hotword Research and Speaker, Voice & Language team,
and a talk on Bidirectional Alignment at amazing UW CIP center, enjoyed the wonderful time and discussion!
Oct-2024 Joined UW iSchool as a Postdoctoral Scholar, and gave a talk at our amazing UW RAISE center about our Bidirectional Alignment research. Excited to return to Seattle and connect with amazing professors, researchers and friends!
Sep-2024 Honored to be selected for the Future Faculty Diversity Program at Virginia Tech, where I gained valuable insights from the professors and leaders. Thank you for having me!
July-2024 Serve as Associate Chairs (AC) for 'Education' and 'Understanding People — Mixed' subcommittees of CHI 2025. Gave a talk at UIUC about our bidirectional alignment research. Thanks for the enjoyable time!
July-2024 Our HypoCompass paper about LLM-baesd Programming Teachable Agent received the Best Paper Award and Best Interactive Event Award. Congrats to all authors!
June-2024 Our Bidirectional Human-AI Alignment survey paper is finally out! Thanks to all my amazing teammates and fabulous advisors, truly wonderful to collaborate with you all!
Mar-2024 Our LLM-based Tutor Agent for Human Debugging paper is accepted by AIED'24. Congrats and Thanks to my dear and amazing coauthors🧡!
Mar-2024 Our Design Space for Intelligent and Interactive Writing Assistants paper is accepted by CHI'24. Congrats and Thanks to our super cool teams and leads🤗!
Jan-2024 Happy to serve as an AC for the CHI 2024 Late Breaking Works and a mentor for NAACL Student Research Workshop 2024☺️.
Dec-2023 Attended EMNLP'23 in person and give a oral talk for my Goolge intern paper and a live demo for my collaborative Gentopia.AI work. Super enjoyed the time learning from excellent researchers and having fun with my loving friends at Singapore!🤗!
Nov-2023 Honored to be selected as one of the President's Postdoctoral Fellowship Program (PPFP) Candidates in UMich and to give a talk about my latest work! Really enjoyed talking with so many amazing professors in UMich CSE, truly appreciate you ALL and my mentors' support🧡!
Nov-2023 Participating and giving a lightning talk at Rising Stars of Data Science located at UChicago. Thanks for having me and meeting you all here 🤗!
Oct-2023 Gave a talk at MISC at Umich. Thank you for the wonderful time and discussion with the amazing professors, researchers, and friends here 🧡!
Oct-2023 Received the Best Demo in CSCW 2023 conference for our ConvXAI work. Thanks a loooot for all your support 🧡!
Oct-2023 Received the Google Research Science Conference Scholarships for our EMNLP 2023 MultiTurnCleanup work. Thank you for Google Research and my dear mentors and managers for supporting me!⭐!
Oct-2023 Selected as one of the 2023 Rising Stars of Data Science hosted by UChicago and UC San Diego. Truly appreciate my dear friend who brought me this great news and dear advisors who recommended me 🧡!
Oct-2023 Our Google AI Research intern work MultiTurnCleanup, and a LLM-agents Demo Gentopia.AI (collaborating with many amazing researchers) have been accepted by EMNLP 2023 main conference and system demonstration. Thanks to my dear mentors and coauthors 🧡!
Sep-2023 Starting my Postdoc research at Umich and enjoying the wonderful people and life🎁 at Ann Arbor🌞!
Aug-2023 Our paper Does Human Collaboration Enhance the Accuracy of Identifying LLM-Generated Deepfake Texts? being accepted by HCOMP2023!🥳 See our new study conducting human collaborative evaluation (i.e., turing test resemblance) on distinguishing LLM-generated v.s. Human-written texts!
Jul-2023 Invited to be the PC member of EMNLP 2023 Industry Track. Thanks for the invitation!
Jul-2023 Excited to give an on-site talk @Carnegie Mellon University and enjoyed the amazing time meeting with the terrific professors and students in Auton Lab. Thank you all!
Jun-2023 I'll attend ACL 2023 in person @Toronto during July 9-14. I'm excited to meet my old and new NLP friends again, and feel free to DM me to meet up!
Jun-2023 Our ConvXAI paper is accepted by CSCW 2023 Demo!🥳 Please see the project combo (i.e., papers, system code, unified XAI API, live demo, and video) of this exciting work :)
Jun-2023 Excited to serve on the PC member of the ICML 2023 AI and HCI Workshop, and reviewer of EMNLP 2023. Thanks for your invitation!
May-2023 Thrilled to give an on-site talk @Princeton University and enjoyed the wonderful time meeting with amazing professors and students in Looking Glass Lab and Visual AI Lab!
Mar-2023 Our ScatterShot paper got Best Paper Honorable Mention Award. Thank you to all my dear co-authors and the IUI chairs!
Mar-2023 Our paper, Parachute: Evaluating Interactive Human-LM Co-writing Systems is accepted by CHI 2023 In2Writing Workshop. Thanks to my advisors' support.
Thrilled to meet my HCI friends @Hamburg this April/2023!
Jan-2023 I gave a talk @Google Research for my intern project. Thanks for my dear mentors' and friends' participation and support!
Dec-2022 I serve as a PC member of the NLP Interpretability Track for ACL 2023. Glad to review amazong works submitted to ACL 2023!
Sep-2022 I'm glad to give a talk at the Notre Dame NL+ seminar on and share our latest work on Human-centered Explainable AI. Look forward to meeting and discussing with Notre Dame NLPer friends!
Sep-2022 I will join Google AI as a researcher intern during the Fall semester. Would love to meet more old and new friends at Seattle again!
Aug-2022 Accepted the reviewer invitation from the NeurIPS 2022 Workshop on Human Evaluation of Generative Models. Looking forward to reviewing the papers in this amazing workshop!
Aug-2022 I passed my Ph.D. comprehensive exam and become a Ph.D. candidate! I appreciate all the valuable feedbacks from my dear committee members including Dr. Ting-hao (Kenneth) Huang, Dr. Mary Beth Rosson, Dr. C. Lee Giles, Dr. S. Shyam Sundar, Dr. Sherry Tongshuang Wu. Thank you all!
July-2022 I'm serving as a review committee member for the Interpretability track at EMNLP 2022. Thank the co-chairs for your nice invitation!
July-2022 I'm attending NAACL 2022 in person. Excited to meeting amazing NLPer friends again at Seattle!
May-2022 I'm joining Amazon Alexa AI ASR Language Modeling team as an applied scientist intern in May and will move to Seattle during the summer!
Apr-2022 I'm attending CHI'22 in person. Looking forward to hanging out with my old and new friends in New Orleans!
Feb-2022 Our short paper, Are Shortest Rationales the Best Explanations for Human Understanding? is accepted by ACL 2022 main conference. Thank you, my co-authors and advisor!
Jan-2022 Our paper, Improving Fairness in Speaker Verification via Group-adapted Fusion Network is accepted by ICASSP 2022. Thank you to all my advisors!
Aug-2021 I am fortunately nominated for Microsoft Research PhD Fellowship by the office of the department chair at The PennState University. Thank you!
May-2021 Our paper on analyzing gaps between user needs and NLP explanations is accepted by CHI'21 HCXAI Workshop as an oral presentation. Our Paper and the Website are available!
Mar-2021 I will join Amazon Alexa AI research group as an Applied Scientist Intern in 2021 summer! I appreciate everyone who helped me and look forward to joining the research team to learn!
Feb-2021 I serve as a PC member of the NLP Interpretability Track for ACL-IJCNLP 2021. Grateful to my First-time ACL reviewer mentor, Dr. Marco Tulio Ribeiro, Thank you, ACL'21!
Feb-2021 PennState IST award for Graduate Student Travel Grant on our AI Interpretation work. Thank you, IST!
Oct-2020 Penn State News wrote a nice post about our AI Interpretation work. Thank you, PennState!
Oct-2020 Our paper on usefulness evaluatation for AI interpretations is accepted by HCOMP 2020!
I will present our work with a talk at HCOMP on Oct 28, 2020.
May-2020 I passed the Ph.D. Qualifying Exam of IST College at PennState!