At the University of Pennsylvania, I developed and refined a Variational Autoencoder (VAE) to reconstruct visual fields, improving both runtime and functionality. I extended the VAE to predict future visual fields, enhancing its clinical applicability. Additionally, I explored the performance of diffusion models in comparison to VAEs for glaucoma progression, focusing on efficiency and accuracy. My work also involved archetypal analysis of visual field data to classify progression patterns and improve model performance. To further optimize results, I integrated CNN structures into the VAE and collaborated closely with PhD students and professors to align computational models with clinical diagnostics.

Supported students in designing and building autonomous robots, focusing on mechanical and electrical systems integration. Assisted in developing 3D-printed and laser-cut robotic chassis, programmed ESP32 microcontrollers, and implemented sensor-based autonomous navigation using time-of-flight (TOF) and ultrasonic sensors. Led the development of modules for light beacon detection and autonomous movement to specified X-Y coordinates.

Served as a Residential Teaching Assistant for a one-month intensive robotics program, guiding high school students in the fundamentals of computer science, mechanical design, and circuitry. Led a class of students through hands-on projects, culminating in the development of a fully functioning robotic orchestra, which included instruments such as piano, bass guitar, and drums.