I am a Ph.D. student at the Department of Computer and Information Science, the University of Pennsylvania, where I work with Duncan Watts at the Computational Social Science Lab. I am also a visiting student at the Mathematics and Computer Science Division, Argonne National Laboratory.

I am broadly interested in developing computational and human-in-the-loop methods to study individual and collective human behavior. Examples of such behavior include moral decision-making and judgment, stance toward socially significant issues, and commonsense knowledge and reasoning. The tools to study them are grounded in network science, natural language processing, social psychology, machine learning and crowdsourcing.

My other interests include mathematical optimization, especially in the context of machine learning. I have collaborated with Nguyen Tran at the School of Computer Science, the University of Sydney, on designing personalized and communication-efficient algorithms for federated learning. Together with other Ph.D. students I have studied several problems in computational optimal transport with applications in machine learning.

Recently I have been studying the capabilities of foundation models in areas involving the generation of novel and specialized knowledge. The problems I am pursuing include hypothesis generation in astronomical research (with Yuan-Sen Ting and the UniverseTBD consortium) and evaluation of language models in various scientific contexts (with Sandeep Madireddy at Argonne).

Prior to joining Penn I was an M.Phil. student at the Computational Media Lab, the Australian National University where I was jointly advised by Lexing Xie (School of Computing) and Colin Klein (School of Philosophy). My thesis presents a series of large-scale studies of online discussions to uncover popular topics of contemporary moral concern, and characterize how moral dilemmas are framed and how they are perceived and judged by internet users. My research was also supported by the Humanising Machine Intelligence Grand Challenge at ANU.

Prior to that I pursued a B.S. in computer science at the School of Computing and Information Systems, the University of Melbourne. During my undergraduate studies, I worked with Charl Ras at the School of Mathematics and Statistics on designing resilient network embeddings.

I publish under my official Vietnamese name, Tuan Dung Nguyen.


[2024-04-05] I presented a talk titled “How Aligned are Humans and Language Models on Common Sense?” at the Generative AI and Social Science Research Workshop at Yale University.

[2024-02-16] I delivered a talk titled “Science Meets AI: Lessons from the Exploration of LLMs in Astronomical Research” at the Planet+AI consortium. The video recording is on YouTube.

[2024-01-29] I will start working at the Mathematics and Computer Science Division, Argonne National Laboratory as a visiting student. Excited to be working with Aurora, Argonne’s flagship exascale supercomputer.

[2024-01-04] AstroLLaMA-chat, a conversational LLM based on our earlier model at UniverseTBD, is released. You can play with it via this Hugging Face space.

[2023-12-09] We have a paper accepted to AAAI 2024 titled On Partial Optimal Transport: Revising the Infeasibility of Sinkhorn and Efficient Gradient Methods. Update: our paper is also selected for oral presentation.

[2023-11-16] Our new paper, titled Measuring Moral Dimensions in Social Media with Mformer, is accepted to ICWSM 2024. Update: our paper is also selected for spotlight presentation.

[2023-09-12] We release a new language model for astronomical research called AstroLLaMA. Joint work with Yuan-Sen Ting and Jo Ciuca at the ANU Research School of Astronomy and many others at UniverseTBD. A short technical report can be found here.

[2023-03-16] This fall I am excited to be joining the University of Pennsylvania as a Ph.D. candidate in computer and information science!

[2022-11-10] I made a YouTube channel! The first video is a lecture on optimal transport I gave to the Advanced ML class at ANU. The slides are here.

[2022-05-12] I gave a talk on our ICWSM 2022 paper at the ANU’s AI, ML and Friends seminar. The slides can be found here. There’s also a press coverage by ANU here.

[2022-03-16] Our paper, Mapping Topics in 100,000 Real-life Moral Dilemmas, is accepted to ICWSM 2022! The code can be found here and data here.

[2021-11-30] I am honored to attend the International School in Artificial Intelligence and its Applications in Computer Science (ISAAC 2021) this december at Monash University.

[2021-04-27] I will be volunteering at the ICWSM-2021 conference.

[2021-04-19] I will be volunteering at the AIES-2021 conference. Thanks HMI for your invitation.

[2021-04-16] I am honored to be selected to the Cornell, Maryland and Max Planck Pre-doctoral Research School (CMMRS-21).

[2020-12-15] Check out our pre-print DONE: Distributed Newton-type Method for Federated Edge Learning on arXiv.

[2020-10-26] Our work, titled Personalized Federated Learning with Moreau Envelopes, is accepted to NeurIPS 2020. The code can be found here.

[2020-05-26] Our paper, Federated Learning with Proximal Stochastic Variance Reduced Gradient Algorithms, is accepted to ICPP 2020.