yyf20001230 / frank_yang

Coding future one algorithm at a time

About

I am currently pursuing a Bachelor's and Master's degree in Computer Science and Mathematics at Northwestern University. In the past, I had the privilege of collaborating with Professor Florian Willomitzer and Oliver Cossairt at the 3DIM Lab, focusing on high-precision 3D image reconstruction. Presently, my efforts are directed towards research with Professor Qi Zhu at the Design Automation of Intelligent Systems Lab, where I am exploring reinforcement learning approaches for safety-critical control systems.

I have a broad interest in computer vision and deep reinforcement learning. This curiosity fuels my research vision — a commitment to contributing to the evolution of self-driving technologies. Whether applied to robotics or commodity vehicles, I envision a future where vehicles navigate roads with an optimal balance of efficiency and safety.

I deeply believe in human ingenuity and the potential of Artificial Intelligence. 10 years from now, I want to be a computer vision scientist, immersing myself in a pioneering industry capable of pushing the limit of autonomous driving.

Please see my CV for a full list of work, teaching, and other experiences.

Publications

Yang, F., Wen, Y. Efficient Encoding of Graphics Primitives with Simplex-based Structures. Midwest Machine Learning Symposium, 2023. Paper

Research

Efficient Encoding of Graphics Primitives with Simplex-based Structures

Advised by: Ying Wu
Surveyed the encoding of graphics primitives proposed by “Instant NGP"; established theoretical foundations for simplex-based structure encodings and accelerated sample and interpolation speed on NeRF and SDF rendering with C++/CUDA kernels

MMLS 2023 / Paper

High-quality 3D imaging with Commodity Devices

Advised by: Florian Willomitzer and Oliver Cossairt
Created a python 3D imaging framework that facilitates non-technical users to discover micro-painting degradation in Kokomo glass test tiles; packaged a 3-step calibration sequencefor Phase Measuring Deflectometry; benchmarked performance with FLIR camera on specular objects

3DIM Lab / Page / Paper

Transformer-based Lie Detection

Advised by: Zach Wood Woughty
Conceptualized a vision-based transformer that detects lies from multimodal inputs with PyTorch; trained a transformer encoder from fine-tuning Inceptionv3; pinpointed 20 micro-gestures and facial AUs that most contribute to lying; resulted an out-of-sample lying classification of 76%

Code

Teaching

Undergraduate TA for CS396: Intro to Web Development taught by Sarah Van Wart, Spring 2022

Graduate TA for CS310: Scalable Software Architectures taught by Joe Hummel, Fall 2023

Project Manager for Institute of Electrical and Electronics Engineers, 2022

Project

Reminiscia

_(Dec 2022 - May 2023)_

Implemented a multimodal text-to-image search application using pretrained vision-language models
Employed Vision and CoreML to allow calculations of cosine similarity between text and image embeddings
Distilled original 224MB CLIP model into an 85MB, 6-layer image encoder to improve inference speed

Northwestern Wildhacks / Code

MatchaNU

_(Jun 2021 - Feb 2022)_

Launched a IOS application to assist Northwestern students with course planning and building navigation
Integrated Google Geocoding API to generate building name from scrapped catalog into geocoordinates
Integrated UIKit with LocationManager in SwiftUI to track location and provide to classrooms navigation
Used by over 1000 Northwestern undergraduates every quarter; making updates from quarterly testing

Code

Single-Len Lightfield imaging

_(Jul 2021 - Feb 2022)_

Introduced an alternative to a light-field camera that synthesizes camera focus point after a video is taken
Researched capturing the light-field from a camera with known parameter with OpenCV
Tested with mirrorless-cam experiments and decreased the functional cost of a light-field camera by 3000%

Code

Work Experiences

Software Engineer Intern @ Target

(June 2023 - Aug 2023)

Developed a Golang application within a Vela CI/CD pipeline to enforce security and compliance standards
Integrated Postgres with RestAPI for build lifecycle and versioning information retrieval and storage
Performed unit and integration testing with sqlmock and httptest, achieved service level objectives (SLOs)

Lead Tech Engineer @ Skuy

(Apr 2022 - Present)

Built a college community network app startup, amassed 500+ users on both the App Store and Google Play
Led a 2-months database migration from Heroku to Firebase for service growth and stability
Managed pull requests for 8 tech engineers to ensure encrypted retrieval and storage for private user info
Configured CI/CD pipeline on Expo for IOS Pod and Android Gradle builds

Software Development Engineering Intern @ Amazon

(Jun 2022 - Sep 2022)

Implemented a Sagemaker site that provides benchmarked health & architecture evaluations for ML models
Simplified frontend of S3 resource selector with React and Redux; unit tested with ESLint and Cypress
Presented a demo to Sagemaker engineers; received candidacy to beta-launch model cards on AWS Re:Invent

Skills

Languages: Python, Go, TypeScript, SwiftUI, HTML/CSS/JavaScript, C++
Deep Learning: Torch, CUDA, TensorFlow, OpenCV
Web/Mobile Development: React, React Native, Flask, Redux, Node, ESLint, Cypress
DevOps: RestAPI, AWS, Firebase, Heroku, Elastic Beanstalk, Git, Vela, Docker, MySQL, PostgresSQL

Photography

Coming soon...