about
I study CS at CMU, specifically in Deep Learning and Robotics. Otherwise, I also like systems and theory-heavy math coursework.
My broad interests are robot learning and generative models. My current focus is to gain more experience in robot learning and gain more knowledge in NLP areas. I am currently conducting research at CMU Robotics Institute related to real2sim cloth folding.
Very eager to connect with you if you share the same interests
todo: add links/demos later
projects
2025
Image Generation Implemented DDPM/DDIM with CFG and VAE encoding trained with UNet on ImageNet-100 with 8xH100s on PSC. Also tried VAE reconstruction on faces.
Household Robot Finetuned VLA (π0.5, SmolVLA) on cloth folding tasks, succeeding almost 100% of time on trained tasks - pretraining allows robot to adapt to disruptions/mistakes as well. Also trained behaviorial cloning (Stanford ACT) on same task + other pick and place tasks.
2024
SLAM Robot Implemented differential drive controller, EKF, sensor fusion, and 2D LiDAR SLAM in ROS2 Humble - simulated in Gazebo.
2023
STEM Competition Web App Designed and built a multiplayer web app for lobbies and competing against players in science bowl/mathcounts Countdown games in real-time before agentic IDEs existed.
when i was more interested in hardware
FRC 7419 (9919) ChargedUp Robot Led the design, fabrication, assembly, and programming of a) omnidirectional drivetrain b) lowered center of gravity c) lower four-bar arm linkage for FRC 7419's offseason "ChargedUp" Robot - This year's game aimed to pick-and-place cube balloons and traffic cones in versatile positions.
Quadcopter FPV Drone A simple wiring, assembly, and installation for a quadcopter FPV drone.