I am an M.S. and B.S. student in Computer Science at Stanford University advised by Dr. Mark Horowitz. I am particularly interested in leveraging large-scale distributed systems to accelerate training and inference for deep learning models. My research is focused on improving the reliability and interpretability of machine learning systems, developing data-centric approaches for offline reinforcement learning and imitation learning, and advancing multimodal visual understanding with applications in biomedicine and neuroscience.
Previously, I was a research assistant at Stanford investigating deep learning for immune cell behavioral modeling supervised by Dr. Barbara Engelhardt and an intern at UC San Francisco studying gene expression prediction supervised by Dr. Tomasz Nowakowski.
Beyond research, I enjoy competing in Kaggle competitions and strategy games such as chess, poker, and golf.
Benchmarked PPO, DDPG, SAC, and TD3 policies on a 1,000 sample states from the Point Maze environment.
View Code →Built a graph neural network recommender system on the Microsoft News Dataset (MIND) to learn user-article click behavior.
View Report →Forecasted daily price changes in binary event contracts backtesting on 10K+ time-series samples from Kalshi.
View Code →Developed a ResNet-18 hardware accelerator with a systolic array, FIFO buffering, and banked memory hierarchy.
Designed a rasterization hardware accelerator with micropolygon bounding, edge traversal, and backface culling.
Developed a five-stage pipelined processor for the MIPS ISA with hazard detection, forwarding, and stall control.
Implemented register renaming logic in a pipelined RISC-V processor to eliminate write after write and write after read hazards.
Benchmarked parity, checksum, and Hamming error-correcting codes in 8×8 2D Torus routers using BookSim.
Defined Intel’s Remote Action Request for remote TLB shootdowns through memory transiency models.
