正在招聘
2026年11月。 正在招聘：数据驱动的 RSI 方向，有模型后训练和模型推理加速优化背景的同学欢迎联系我：wubeen@outlook.com。
个人简介
Bin Wu 是阿里云数据库与存储实验室的研究科学家 / 高级技术研究专家。他的工作是把 Data+AI 研究推进到生产：在顶级会议上提出新方法，并把这些方法大规模部署出去，用来解决关键业务问题。目前的研究集中在 Agentic RAG、NL2SQL 和 AI Agent，同时也关注理论计算机科学与大规模数据库管理系统。
此前，他曾在华为诺亚方舟实验室担任研究员。2017 年于香港科技大学（HKUST）获得计算机科学博士学位，导师是 Prof. Ke Yi，2012 年于复旦大学获得学士学位。他曾获得 ACM SIGMOD 最佳论文奖（2016）和 ACM SIGMOD 研究亮点奖（2017）。
研究兴趣
Agentic RAG、NL2SQL 与 AI Agent
OLAP 算法与系统
查询优化
工作经历
研究科学家 / 高级技术研究专家
阿里云，阿里巴巴集团
推动 Data+AI 研究落地到生产：在顶级会议发表新方法，并规模化部署以解决关键业务问题。
研究员
华为诺亚方舟实验室
开展元学习与小样本学习研究，并在真实问题上验证方法。
教育经历
计算机科学博士
香港科技大学（HKUST）
导师为 Prof. Ke Yi。研究方向为近似查询处理与流算法。
计算机科学学士
复旦大学
荣誉奖项
ACM SIGMOD 研究亮点奖
ACM SIGMOD ∙
2017年
表彰突出的研究贡献。
ACM SIGMOD 最佳论文奖
ACM SIGMOD ∙
2016年
数据库领域顶级会议的最佳论文奖。
代表论文
(2025).
Andromeda: Debugging Database Performance Issues with Retrieval-Augmented Large Language Models.
Companion of the 2025 International Conference on Management of Data (SIGMOD 2025).
(2023).
Anser: Adaptive Information Sharing Framework of AnalyticDB.
Proceedings of the VLDB Endowment, 16(12), 2023.
(2023).
ShapleyIQ: Influence Quantification by Shapley Values for Performance Debugging of Microservices.
Proceedings of the 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS 2023).
(2023).
CatSQL: Towards Real World Natural Language to SQL Applications.
Proceedings of the VLDB Endowment, 16(6), 2023.
(2020).
AnalyticDB-V: A Hybrid Analytical Engine Towards Query Fusion for Structured and Unstructured Data.
Proceedings of the VLDB Endowment, 13(12), 2020.
(2016).
Wander Join: Online Aggregation via Random Walks.
Proceedings of the 2016 International Conference on Management of Data (SIGMOD 2016).
(2026).
PolarStore: High-Performance Data Compression for Large-Scale Cloud-Native Databases.
24th USENIX Conference on File and Storage Technologies (FAST 2026).
(2023).
Lindorm TSDB: A Cloud-Native Time-Series Database for Large-Scale Monitoring Systems.
Proceedings of the VLDB Endowment, 16(12), 2023.
(2023).
Active Sampling for Sparse Table by Bayesian Optimization with Adaptive Resolution.
IEEE 39th International Conference on Data Engineering (ICDE 2023).
(2023).
OneShotSTL: One-Shot Seasonal-Trend Decomposition for Online Time Series Anomaly Detection and Forecasting.
Proceedings of the VLDB Endowment, 16(6), 2023.
(2023).
Learning-Based Query Optimization for Multi-Probe Approximate Nearest Neighbor Search.
The VLDB Journal, 32(3), 2023.
(2022).
Releasing Private Data for Numerical Queries.
Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2022).
(2021).
Cquirrel: Continuous Query Processing over Acyclic Relational Schemas.
Proceedings of the VLDB Endowment, 14(12), 2021.
(2021).
Weighted Distinct Sampling: Cardinality Estimation for SPJ Queries.
Proceedings of the 2021 International Conference on Management of Data (SIGMOD 2021).
(2019).
Wander Join and XDB: Online Aggregation via Random Walks.
ACM Transactions on Database Systems (TODS), 44(1), 2019.
(2018).
Deep Meta-Learning: Learning to Learn in the Concept Space.
arXiv preprint arXiv:1802.03596, 2018.
(2017).
Wander Join and XDB: Online Aggregation via Random Walks.
ACM SIGMOD Record, 46(1), 2017 (Research Highlight).
(2016).
Counting Triangles in Large Graphs by Random Sampling.
IEEE Transactions on Knowledge and Data Engineering, 28(8), 2016.
(2016).
Wander Join: Online Aggregation for Joins.
Proceedings of the 2016 International Conference on Management of Data (SIGMOD 2016, Demo).
(2011).
Correlative Multi-Label Multi-Instance Image Annotation.
2011 International Conference on Computer Vision (ICCV 2011).
(2011).
Multi-Kernel Multi-Label Learning with Max-Margin Concept Network.
IJCAI 2011.