Yuxuan Yang
Los Angeles, California, United States
Summary
🤩
Rockstar🎓
Top SchoolYuxuan Yang is an electrical engineer and emerging software practitioner with four years of hands-on experience across embedded systems, PCB design, and laboratory instruction. Educated at SJTU (BE) and currently pursuing an MS at USC, he has implemented STM32-based firmware, designed PCB schematics in KiCad, and prototyped communication via UART and I2C for medical-device testing. His internships include practical high-voltage measurement techniques and proposing simple, effective methods for motor winding ratio testing, reflecting a knack for pragmatic problem-solving. As a teaching assistant, he’s communicated technical concepts clearly to undergraduates, blending mentorship with rigorous grading and lab oversight. Recently exploring LLM agents and multi-agent systems on GitHub, he pairs hardware fluency with growing interest in AI-driven coordination, positioning him at the intersection of embedded systems and intelligent automation.
4 years of coding experience
Master of Science - MS, Electrical and Electronics Engineering, Master of Science - MS, Electrical and Electronics Engineering at University of Southern CaliforniaBachelor of Engineering - BE, Electrical and Computer Engineering, Bachelor of Engineering - BE, Electrical and Computer Engineering at UM-SJTU Joint Institute, Shanghai Jiao Tong University
Chinese, English, Japanese
Github Skills (15)
few-shot-learning8
benchmark6
llm5
reinforcement-learning5
huggingface5
multimodal5
decentralization5
artificial-intelligence4
agent4
natural-language-processing4
large-language-models4
gpt3
multi-agent3
chatgpt3
information-theory2
Programming languages (1)
Github contributions (5)
zoe-yyx/AgentNet
Jul 2025 - Oct 2025
[NIPS2025] A decentralized, RAG-enhanced multi-agent framework for LLMs with dynamic task routing and agent evolution.
Contributions:25 pushes, 1 branch in 2 months
multi-agentcoordinationdecentralizationfew-shot-learningllm
zoe-yyx/CapaBench
Jan 2025 - May 2025
Capabench：A Game-Theoretic Evaluation Benchmark for Modular Attribution in LLM Agents
Contributions:23 pushes in 3 months
llm
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.