Postdoctoral Researcher
>
Scalable Parallel Computing Laboratory, Computer Science Department, ETH Zürich
Email: jianyang.gao [at] inf.ethz.ch
Andreasstrasse 5, 8050 Zürich
Jianyang is a Postdoctoral Researcher at ETH Zürich, hosted by Prof. Torsten Hoefler.
Before that he was a research fellow at Nanyang Technological University. He got the Ph.D. degree under the supervision of Prof. Cheng Long from Nanyang Technological University in 2025 and the Bachelor's degree in Mathematics from Beijing Normal University in 2021. At Nanyang Technological University, he was also fortunate to learn elegant theories from Prof. Yi Li and Prof. Yufei Tao.
Jianyang is interested in designing algorithms with rigorous theoretical guarantees for vector database systems, machine learning systems and large language models.
The RaBitQ Library - A lightweight library for the RaBitQ algorithm and its applications in vector search.[Code][Docs][Technical Report at VecDB@ICML2025]
Jifan Shi, Jianyang Gao, James Xia, Tamás Béla Fehér, Cheng Long, "GPU-Native Approximate Nearest Neighbor Search with IVF-RaBitQ: Fast Index Build and Search" Preprint 2026 [arXiv.][Code]
Yongyi Yang*, Jianyang Gao* , "mHC-lite: You Don't Need 20 Sinkhorn-Knopp Iterations" Preprint 2026 [arXiv.][Code]
Yongyi Yang, Jianyang Gao , Wei Hu, "RaanA: A Fast, Flexible, and Data-Efficient Post-Training Quantization Algorithm" Preprint 2025, ER@NeurIPS 2025 [arXiv.][Code]
Jianyang Gao, Yutong Gou, Yuexuan Xu, Yongyi Yang, Cheng Long, Raymond Chi-Wing Wong, "Practical and Asymptotically Optimal Quantization of High-Dimensional Vectors in Euclidean Space for Approximate Nearest Neighbor Search" arXiv preprint arXiv:2409.09913 (September, 2024). To appear in Proceedings of ACM International Conference on Management of Data (SIGMOD) 2025. [arXiv][Code]
Yutong Gou*, Jianyang Gao*, Yuexuan Xu, Cheng Long, "SymphonyQG: towards Symphonious Integration of Quantization and Graph for Approximate Nearest Neighbor Search", Proceedings of ACM International Conference on Management of Data (SIGMOD) 2025. [arXiv][Proc.][Code]
Yuexuan Xu*, Jianyang Gao*, Yutong Gou, Cheng Long, Christian S Jensen, "iRangeGraph: Improvising Range-dedicated Graphs for Range-filtering Nearest Neighbor Search", Proceedings of ACM International Conference on Management of Data (SIGMOD) 2025. [arXiv][Proc.][Code]
Ziqi Yin, Jianyang Gao, Pasquale Balsebre, Cong Gao, Cheng Long, "DEG: Efficient Hybrid Vector Search Using the Dynamic Edge Navigation Graph", Proceedings of ACM International Conference on Management of Data (SIGMOD) 2025. [Proc.][Code]
Jianyang Gao, Yutong Gou, Yuexuan Xu, Jifan Shi, Cheng Long, Raymond Chi-Wing Wong, Themis Palpanas, "High-Dimensional Vector Quantization: General Framework, Recent Advances, and Future Directions" IEEE Data Eng. Bull. 2024 [Proc.]
Jianyang Gao, Cheng Long, "RaBitQ: Quantizing High-Dimensional Vectors with a Theoretical Error Bound for Approximate Nearest Neighbor Search", Proceedings of ACM International Conference on Management of Data (SIGMOD) 2024. [arXiv][Proc.][Code]
Jianyang Gao, Cheng Long, "High-Dimensional Approximate Nearest Neighbor Search: with Reliable and Efficient Distance Comparison Operations", Proceedings of ACM International Conference on Management of Data (SIGMOD) 2023. [arXiv][Proc.][Code]
CCDS Outstanding PhD Thesis Award (one of two awardees), at Nanyang Technological University, 2025 .
Travel Grant, at SIGMOD, 2024.
62rd Place, at ICPC World Finals, 2019.
RaBitQ: Practical and Asymptotically Optimal Quantization of High-Dimensional Vectors at FOCS 2025 ANNS Workshop (Dec-25)
The RaBitQ Project at Ant Group (Jan-25); Zilliz (Jan-25); Bangaluru System Meetups (Mar-25); Microsoft (Apr-25); SUSTech (Jul-25); Meta (Aug-25)
Quantizing High-Dimensional Vectors with a Theoretical Error Bound for Approximate Nearest Neighbor Search at Huawei Data Storage Technology Planning Dept (Aug-24); Huawei Theory Lab (Sep-24); ByteDance (Sep-24)
Approximate Nearest Neighbor Search with Reliable Distance Comparison and Estimation at Huawei Cloud Database Innovation Lab (July-24)
Approximate Nearest Neighbor Search with Reliable Distance Comparison at ByteDance (Oct-23)
Program Committee Members / Reviewers
2027: SIGMOD (Light-Load Fast-Response (LLFR) Reviewers), ICML
2026: ICDE
Journal Reviewer
WWWJ, TKDE, TC
External Reviewer
2024: SIGMOD, VLDB, ICDE, SDM
2023: SIGMOD, ICDE, TKDE
2022: SIGMOD(demo), VLDB, ICDE