Research

AI4X 2025 International Conference | First Author

Quantifying Uncertainty in Physics-Informed Neural Networks

We used deep evidential regression to quantify uncertainties in physics-informed neural networks, demonstrating it on the Burgers and Laplace experiments.

abstractWe integrate a state-of-the-art method to quantify aleatoric and epistemic uncertainties in physics-informed neural networks and observe that they can be captured effectively while maintaining predictive accuracy.

Avaliable at: Paper

Physics-Informed Neural NetworksUncertainty Quantification

Education

Nanyang Technological University |

Bachelor of Engineering (Honours), Computer Engineering

Elective Focus in Security & Artificial Intelligence
Minor in Business

Experience

DSBJ Pte. Ltd.

Jan 2024 - Jul 2024

Application & Data Developer Intern

Implemented a model visualization and analysis platform with Al-driven insights in Python and Nextjs, enabling business units and data scientists to interact with and evaluate mathematical optimization and Al models.
Established a robust Single Sign On (SSO) backend framework, and unified authentication for two existing projects.
Designed an LLM-powered system using LangChain to extract insights from unstructured data.

Next.jsNestJSFastAPIPythonTypescriptPostgreSQL

Works Pte. Ltd.

Feb 2021 - Jul 2021

Mobile Application & Web Application Developer, Intern

Began as a Flutter mobile developer, brought onto Angular web team, and contributed 80% of the total codebase.
Collaborated to create features for both platforms, such as a chat interface, payment processing pages, mobile responsive Ul and other frontend Ul updates, ensuring cross platform feature parity.
Diagnosed and resolved user-reported bugs, eliminating 90% of non-fatal frontend errors in two weeks.

FlutterAngularDartTypescriptFirebase