Hello world, my name is

In this project, we built a simulation framework for customs selection considering the needs of customs administration. We also proposed a new selection strategy based on state‑of‑the‑art exploration and exploitation strategies and proposed an RL-based method to tune the strategy. Long‑term benefit of exploration strategy on realistic simulation setting is examined.

We propose Geospatial INformation Encoded statistical downscaling (GINE), a new method for downscaling (super-resolution) climate simulations. GINE provides two model-agnostic add-on modules for CNN-based super resolution model: Geospatial Guided Attention Module and Localization Guided Augmentation Module. The method provided more fine-grained climate data with useful regional information while preserving the characteristics of the climate simulation results.

This is a term project for CS473 - Introduction to Social Computing. The project was a web service focused on music jamming to encourage social engagement as well as help beginner improve their musical confidence. The interface supports exploration and viewing of existing jams, creation of new jams and collaboration on existing jam.

This work proposes a probabilistic programming method to quantify the efficiency of major non-pharmaceutical interventions. We present a generative simulation model that accounts for the economic and human capital cost of adopting such strategies, and provide an end-to-end pipeline to simulate the virus spread and the incurred loss of various policy combinations.