I am passionate about and have a firm foundation in Machine Learning, and Multimodal Perception. Much of my experience is in applying these technologies to enhance autonomous or defense capabilities.

Research papers that excite me: CLIP, VLMaps, YOLO, CICERO, LLMs play Starcraft 2,FoundationPose

Background

I received my BSEE from UIUC ECE and my MSEE from UW ECE. At UW, I built a strong background in machine learning, deep learning, and computer vision by working as a ML/AI Research Assistant in several labs and through courses. For one of my assistantships I built synthetic data generation and evaluation pipelines for foundation model pose estimation, achieving sub-mm translation error and sub-degree rotation error, enabling robots to successfully grasp unseen objects.

At Sandia National Laboratories, as a R&D ML intern, I trained and evaluated a CNN that uses uncertainty estimation to detect unseen anomalies in national security devices, achieving a recall of 100%. As a R&D ML Intern at Los Alamos National Laboratories, I tuned a CVAE to achieve an average of 80% more accurate reconstruction of shock signals over traditional methods. I also engineered an ensemble modeling approach using various models (CVAE, Diffusion) and synthetic data to generate varying realistic signals. I am now an incoming Machine Learning Engineer at AeroVironment, where I’ll be working on object detection and tracking for drones.

I also have a strong background in Data Structures & Algorithms and make YouTube videos that visually explain important algorithms: study2simple