Chunwei Liu
Department of Computer Science, Purdue University
LWSN 2142D • 305 N. University Street, West Lafayette, IN
chunwei@purdue.edu
Short Bio
Chunwei Liu is an Assistant Professor of the Computer Science Department at Purdue University. His research interests span compound AI systems, database systems, cloud/edge computing, and database benchmarking. He focuses on optimizing data systems for both conventional data analytics and emerging AI-powered agentic pipelines. Chunwei develops privacy-preserving workload generation techniques for evaluating cloud database systems, collaborating with major cloud vendors. Additionally, he devises query-friendly data compression methods for data systems and implements adaptive compression selection in both conventional and resource-constrained databases and machine learning systems. Furthermore, he is engaged in high-dimensional data analysis, with a particular emphasis on time series applications.
He was a Postdoctoral Associate in DSG at MIT CSAIL. He earned his Ph.D. from the Department of Computer Science at the University of Chicago, where he worked in the ChiData group.
News
- Jun 2025Our paper on cloud analytics workload synthesis tool, “PBench: Workload Synthesizer with Real Statistics for Cloud Analytics Benchmarking,” accepted by VLDB 2025.
- Jun 2025Our paper on non-intrusive DBMS scheduling, “Improving DBMS Scheduling Decisions with Accurate Performance Prediction on Concurrent Queries,” accepted by VLDB 2025.
- Jun 2025Our comprehensive study of floating-point compression, “Beyond Compression: A Comprehensive Evaluation of Lossless Floating-Point Compression,” accepted by VLDB 2025.
- Mar 2025Our demo paper on a chat interface for declarative AI frameworks, “PalimpChat: Declarative and Interactive AI Analytics,” accepted by SIGMOD 2025.
- Feb 2025Our paper on scientific discovery “Variable Extraction for Model Recovery in Scientific Literature” accepted by AISD @ NAACL 2025.
- Feb 2025Our paper on open columnar formats evaluation “Data Formats in Analytical DBMSs: Performance Trade-offs and Future Directions” accepted by the VLDB Journal special issue “Best of VLDB.”
- Jan 2025Our paper on LLM scheduling “Don't Stop Me Now: Embedding Based Scheduling for LLMs” accepted to ICLR 2025.
Publications
Professional Service
Service Roles
- Program Committee: SIGMOD'25-27, VLDB'24-27, ICDE'26, KDD'2023, SMDB'2023
- Reviewer: The International Journal on Very Large Data Bases (VLDBJ) since 2022
- Co-Chair: NOVAS Workshop at SIGMOD 2025 and VLDB 2026
- PC Member: 1st International Workshop on Data FORMATS for Modern Architectures at SIGMOD 2026
- Committee: SIGMOD Availability & Reproducibility Committee 2022, 2023
Awards
- GUIDEAI@SIGMOD Best Paper Award 2024
- VLDB Best Paper Runner-Up 2023
- University Unrestricted Fellowship 2019
Teaching
- CS 59200-DMA: Data Management for AI (Purdue, Fall 2025)
- CS 54100: Database Systems (Purdue, Spring 2026)
- CS 44000: Large Scale Data Analytics (Purdue, Fall 2026)
Prospective Students
I am looking for motivated Ph.D. students interested in Data Management and AI. If you are interested in joining my group at Purdue, please apply to the Purdue CS Graduate Program and list me as a potential advisor. You may also reach out via email with your CV and a brief description of your research interests and relevant experience.