Yuqun Zhang
Associate Professor
Austin, Texas, United States
Summary
🤩
Rockstar🎓
Top SchoolYuqun Zhang is an Associate Professor and former UT Austin Ph.D. researcher with seven years of professional experience bridging software engineering, AI, and communications systems. She has a strong systems and programming background (Java, C/C++, Python, R) and a track record of building simulators, routing protocols, and data-centric process tools used to evaluate and improve real-world business and network processes. Her research and teaching span artificial intelligence and software engineering, and she contributes to ML engineering work on long-context Llama-2 summarization and benchmarking in a prominent open-source “Llama Cookbook” repository. Comfortable across Linux and Windows environments and tools from NS-2 to Omnet++, she pairs rigorous academic research with practical implementation skills and clear communication. An uncommon blend for an academic, she has hands-on enterprise IT consultancy experience (Oracle EBS/BIEE) that informs her pragmatic approach to research impact.
7 years of coding experience
16 years of employment as a software developer
PhD, Software Engineering, PhD, Software Engineering at The University of Texas at AustinBachelor of Science, Communications Engineering, Bachelor of Science, Communications Engineering at Tianjin UniversityMaster of Science, Electircal and Computer Engineering, Master of Science, Electircal and Computer Engineering at University of Rochester
Chinese, English
Github Skills (7)
llama10
pytorch10
python10
fine-tuning10
llm9
machine-learning9
caching9
Programming languages (2)
Github contributions (5)
meta-llama/llama-cookbook
Feb 2024 - Apr 2024
Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama model family and using them on various provider services
Role in this project:
ML Engineer
ML EngineerContributions:1 review, 1 PR, 1 comment in 2 months
Contributions summary:Yuqun focused on benchmarking summarization tasks within the context of a Llama-2 model. They implemented and updated code related to H2O Llama, a custom implementation likely designed for long-context tasks, modifying files such as `utils_llama.py`, `generation.py`, and `cache_utils.py`. The commits involved modifying model configurations, generation scripts, and caching mechanisms to optimize for long-context processing and heavy-hitter oracle strategies. This work aimed to improve performance and explore the practical applications of Llama models for summarization.
aifinetuninglangchainllamallama2
Shiweiliuiiiiiii/fairseq
Sep 2022 - Sep 2022
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
Contributions:133 commits, 129 pushes in 8 days
nlpsequencepythonmachine-learningfacebook
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.