DB4AI

We design database systems to better support AI applications and workloads.

1. Hybrid Search

• DEG: Efficient Hybrid Vector Search Using the Dynamic Edge Navigation Graph.
  Ziqi Yin, Jianyang Gao, Pasquale Balsebre, Gao Cong, Long Cheng.
  SIGMOD 2025.

• GeoBloom: Revisiting Lightweight Models for Geographic Information Retrieval.
  Yi Li, Gao Cong.
  PVLDB 2025.

2. Multimodal LSM Storage

• SOLAR: Efficient Spatial Queries on LSM-based Storage. Jingyi Yang, Jiachen Shi, Jian Chen, Gao Cong. ICDE 2026.

• NEXT: A New Secondary Index Framework for LSM-based Data Storage. Jiachen Shi, Jingyi Yang, Gao Cong, and Xiao-Li Li.
  SIGMOD 2025.

• CAMAL: Optimizing LSM-trees via Active Learning.
  Weiping Yu, Siqiang Luo, Zihao Yu, Gao Cong.
  SIGMOD 2025.

3. Semantic Queries & Data Agent

• Demonstrating TOFFEE: A Learned System for Synthesizing Data Agent Trajectories at Scale. Ziting Wang, Yin Li, Zuhao Yang, Xiuchang Li, Jiale Bai, Gao Cong. VLDB 2026 Demonstration.

• FDABench: A Benchmark for Data Agents on Analytical Queries over Heterogeneous Data. Ziting Wang, Shize Zhang, Haitao Yuan, Jinwei Zhu, Wei Dong, Gao Cong. KDD 2026.

• CARROT: A Learned Cost-Constrained Retrieval Optimization System for RAG. Ziting Wang, Haitao Yuan, Wei Dong, Gao Cong, Feifei Li. ICDE 2026.