Research Interests
Currently, I'm leading a team of students working on Database Systems for the Cloud and Large Language Models, including Disaggregated Databases and Vector Databases.
-
Disaggregated Database Systems (for the Cloud)
- Memory-Disaggregated Databases
- Storage-Disaggregated Databases
- Distributed Shared-Memory & Shared-Storage Databases
- Serverless Databases with Disaggregation
- Disaggregated Databases for Data Lakes
- [Papers: SIGMOD'26a, SIGMOD'26b, VLDB'25, Patent'24, SIGMOD'24a, SIGMOD'24b, VLDBJ'24a, VLDB'23, SIGMOD'23, ICDE'23]
- [Major Open-source: We built OpenAurora, an open-source version of Amazon Aurora, based on PostgreSQL v13.0. OpenAurora is a cloud-native database prototype optimized for the storage-disaggregated infrastructure. We hope it can be used by the broader database system research community.]
- [External Grants: NSF CAREER Award]
-
Vector Database Systems (for Large Language Models)
- Supporting Vector Data Management inside Relational Databases
- Multi-Model Vector Databases (Vector + "X") for Advanced RAGs
- Cost-Efficient Vector Databases
- Auto Tuning in Vector Databases
- Beyond Vector Databases: RAGs and Multi-Model Databases
- [Papers: CIDR'26, SIGMOD'26c, SIGMOD'25, VLDB'24a,
VLDB'24b, SIGMOD'24c, SIGMOD'24d, ICDE'24, VLDBJ'24b, SIGMOD'21, ICDT'19]
- [Major Open-source: We built PostgreSQL-V, an integrated vector database system within PostgreSQL. It achieves performance comparable to specialized vector databases and is much faster than pgvector. Check out our CIDR'26 paper for more details. This is towards our broader vision of building data infrastructures for AI.]
|
