I develop foundational and applied methods in probabilistic machine learning, emphasizing questions on measurement, preference, and decision. Specifically, I leverage generative models and adaptive algorithms to design efficient and reliable systems capable of operating in real-world environments. I then apply these methods downstream to challenging applications in machine learning systems and education.
Selected Works
-
Drug Discovery from Human Preferences
ICLR Workshop on Human-AI Coevolution (2025)
Spotlight Paper Talk Code -
Machine Learning from Human Preferences
The Living Textbook (2025)
Paper Talk Code -
Prediction of Item Difficulty for Reading Comprehension Items by Creation of Annotated Item Repository
arXiv (2025)
Paper Code -
Red Teaming ChatGPT in Medicine to Yield Real-World Insights on Model Behavior
Nature Digital Medicine (2025)
-
Reliable and Efficient Amortized Model-based Evaluation
ICLR 20205 Workshop Foundation Models in the Wild (2025)
Spotlight Paper Talk Code -
An Experimental Design Framework for Label-Efficient Supervised Finetuning of Large Language Models
ACL (2024)
-
Crossing Linguistic Horizons: Finetuning and Comprehensive Evaluation of Vietnamese Large Language Models
NAACL (2024)
Paper Code Media -
GAUCHE: A Library for Gaussian Processes in Chemistry
NeurIPS (2024)
Paper -
DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models
NeurIPS (2023)
Best Paper Award Paper Code -
Quantum Neural Architecture Search with Quantum Circuits Metric and Bayesian Optimization
arXiv (2022)
Paper -
Silver Nanoparticle Loaded TiO₂ Nanotubes with High Photocatalytic and Antibacterial Activity Synthesized by Photoreduction Method
Journal of Photochemistry and Photobiology A: Chemistry (2018)
No matching items