Research Interests

Bayesian statistics and its extensions.

Conference Travels

Academic Conferences

Industry Conferences

Publications

Preprints & Manuscripts Under Review

Rethinking LLM-Judged Helpfulness as a Pedagogy Signal: A Pre-Registered Audit Across Tutor Models

Authors: Shuyi Fan*, Boyuan Deng*, Mengyu Xu*, Jiale Liu, Hongyang Zhang, Qiaoxin Yang, Chongyang Gao

* Equal contribution. arXiv preprint, 2026.

[arXiv] [Code]

Operator-Informed Gaussian Processes for Complex Helmholtz Wavefields: From Synthetic Benchmarks to In Vivo Brain Elastography

Authors: Boyuan Deng, Kshitiz Upadhyay, Michael Shields

arXiv preprint, 2026.

[arXiv] [Code]

Peer Reviewed Journal Articles

Title of Journal Article

Authors: Name, Co-author 1, Co-author 2

Brief description of the journal article...

[PDF] [DOI]

Conference Papers & Proceedings

NewInML Workshop @ NeurIPS 2026 Poster

Difference-in-Differences on a Censored Rating Scale Can Manufacture an Effect: Evidence from a Pre-Registered LLM-Judge Audit

Shuyi Fan*, Boyuan Deng*, Mengyu Xu*, Xinhong Xie, Chenyang Li, Hongyang Zhang

* Equal contribution. Accepted for poster presentation.

arXiv Code

Lectures & Presentations

Conference and Seminar Talks (in chronological order)

[1]
"PINN-DGP: Coupling Physics-Informed Neural Networks with Deep Gaussian Processes for Uncertainty-Calibrated Parameter Discovery", EMI, University of Colorado Boulder, 2026
[2]
"Physics-Informed Gaussian Processes for Solving the Helmholtz Equation", NCS20, University of Pennsylvania, 2026
[Program]

Poster Presentations (in chronological order)

[1]
"Physics-Informed Gaussian Processes for Solving the Helmholtz Equation", HEMI Day, Johns Hopkins University, 2026
[Program]