About Me
Passionate about creating innovative solutions through cutting-edge technology and research.
Hello! I'm Yu-Wei Chang
Pioneering embodied AI and VLA research at UCLA to bridge the gap between foundation models and physical world deployment. Architecting scalable systems that enable next-generation robotic autonomy and human-robot collaboration.
Projects Completed
Years Experience
Technologies Used
"I know I'm asking a lot, but the price of freedom is high, it always has been, and it's a price I'm willing to pay. And if I'm the only one, then so be it. But I'm willing to bet I'm not."
Research & Projects
Exploring the intersection of research and development through innovative projects and cutting-edge solutions.
Developed VisCoder Bench, a standardized suite of 50 executable CV tasks (Geometric, Generative, Classical) to evaluate multimodal agents. Dockerized evaluation infrastructure on A100 GPUs, integrating 10+ CV pipelines with PSNR/mAP and VLM-Judge (87% human alignment). Analyzed 900+ trajectories, showing visual grounding improves geometric task success by 4.3x, exposing critical gaps in LLM reasoning. (Under Review, CVPR 2026)
Componentized architecture for personalized robot control using adapter conditioning on user embeddings for O(1) personalization.
Prompt engineering framework that analyzes user interaction videos to extract preferences, adapting robot behavior without retraining.
Driverless USB HID firmware and custom packet protocol, optimizing flash write throughput to reduce programming time by 80%.
Professional Experience
A journey through diverse roles and challenging projects that have shaped my expertise in software development and research.
Shin-Da Information Co., Ltd.
Built a Python serverless backend on AWS, optimizing transaction latency and engineered an automated ETL data validation pipeline.
Marker X Biomedical Co., Ltd
Architected a centralized PostgreSQL data lake and developed high-throughput analysis pipelines for mass spectrometry data.
Industrial Technology Research Institute (ITRI)
Engineered a RAG-based memory system for elder-care robots and deployed a multi-modal AI agent platform.
Educational Journey
My academic foundation and continuous learning path that shaped my expertise in technology and research.
Master's Student
Electrical and Computer Engineering
University of California, Los Angeles
Bachelor's Degree
Electrical and Computer Engineering
National Tsing Hua University
Teaching Experience
Graduate Teaching Assistant
Neural Networks & Deep Learning (ECE C147/C247)
Academic Background
Formal education and key milestones
Electrical and Computer Engineering
Cumulative GPA: 3.88/4.0. Graduate Teaching Assistant.
Academic Achievements
Electrical Engineering
Cumulative GPA: 4.04/4.3. Coursework: Computer Vision, Machine Learning, Deep Reinforcement Learning, Algorithms, Control Systems, Computer Architecture.
Academic Achievements
Learning Philosophy
"Education is not just about acquiring knowledge, but about developing the ability to think critically, solve complex problems, and adapt to an ever-changing technological landscape."
Get In Touch
Have a project in mind or want to collaborate? I'd love to hear from you. Let's create something amazing together.
Let's Connect
I'm always interested in new opportunities, collaborations, and interesting projects. Feel free to reach out!
eesoymilk@gmail.com
Location
Los Angeles, CA
Phone
+1 (310) 280-6463