Shunjie "Kyle" Hu
Computer science
Hometown: Shanghai, Shanghai, China
Graduation date: Fall 2026
Additional details: Transfer student
FURI | Spring 2025
A Benchmark Suite for Evaluating AI/ML Inference Queries
Inference queries that nest AI/ML model inferences and SQL queries, such as SELECT tid, cid FROM transactions, customers, WHERE transactions.cid = customers.id AND dnn_predict(transactions.*, customers.*) = FALSE, is urgently demanded in various industries, such as retailing, healthcare, finance, and homeland security, for personalized product recommendation, conversational intelligence, fraud detection, etc. These applications all rely on performing AI/ML inferences over relational databases. A lot of systems supporting inference queries emerged recently, such as Amazon Redshift, Google BigQuery, GaussML, Raven, EvaDB, PostgresML, and so on. However, existing AI/ML benchmarks such as MLPerf focus on the AI/ML performance, while database benchmarks such as TPC-H and TPC-DS focus on query performance. There is a lack of a high-quality benchmark for inference queries and for comparing the performance of different systems that support and optimize such queries or different optimization algorithms that co-optimize SQL and ML.
To address the problem, our research will present a new and comprehensive benchmark suite, which will provide 100 inference queries ranging from simple to complex in query logic and model complexity. These queries consist of different numbers and different types of AI/ML models, and different numbers and different types of relational operators. These queries are built on real-world datasets such as IMDB. They will support realistic AI/ML models ranging from simple linear regression models and decision tree models to complex deep neural network models, convolutional models, transformer models, and LLM models.
Mentor: Jia Zou
It’s hip to be square.
Students presenting projects at the Fulton Forge Student Research Expo are encouraged to download this personal QR code and include it within your poster. This allows expo attendees to explore more about your project and about you in the future.
Right click the image to save it to your computer.
Featured project | Spring 2025
Kyle Hu, a computer science undergraduate student, joined the spring 2025 FURI cohort because he desired to gain experience working with databases and artificial intelligence, or AI, research. Working under his faculty mentor Jia Zou, a Fulton Schools assistant professor of computer science and engineering, Hu is creating new standards for processes in machine learning, a type of AI, to speed up algorithms’ performance and reduce their power consumption.
What made you want to get involved in this program? Why did you choose the project you’re working on?
I wanted hands-on databases and AI-related research experience to build upon my programming skills. This project aligned with my interests in database AI optimization and large-scale data processing challenges.
How will your engineering research project impact the world?
My project benchmarks AI inference databases, helping developers optimize performance, improve efficiency and make informed decisions for real-world AI applications to reduce tremendous energy consumption.
Have there been any surprises in your research?
Yes. I’m doing research that is the first of its kind. There is no precedent, as existing benchmarks didn’t fully fulfill real-world inference workloads. I’m innovating a new comprehensive benchmark for the AI era.
How do you see this experience helping with your career or advanced degree goals?
It strengthens my understanding of database systems, programming skills, benchmarking methodologies and performance optimization, preparing me for research or industry roles.
Why should other students get involved in this program?
It provides hands-on research experience, technical growth and mentorship, allowing students to contribute to cutting-edge AI technology and database optimization and more, depending on your field of interest.
