DBScholar

Back to papers

VecFlow: A High-Performance Vector Data Management System for Filtered-Search on GPUs

Summary: VecFlow is a GPU-based, label-centric vector-filtered search system boosting filter selectivity for ANNS. Architecture-aware optimization and batch support deliver throughput and recall, reaching 5M QPS at 90% recall with up to 135x CPU gains over DiskANN. (summarized by gpt-5-nano on Feb 09 2026)

Paper ID
h5353b11e8b4827e1
Venue
SIGMOD
Year
2026
Pagerank
5.4035152e-05
Overall Rank
8,032 | 46.00%
DOI
10.1145/3749189

Incoming Non-self Citations Over Time

Authors

BibTeX Citation

@inproceedings{xi_sigmod26,
        title = {{VecFlow: A High-Performance Vector Data Management System for Filtered-Search on GPUs}},
        author = {Xi, Jingyi and Mo, Chenghao and Karsin, Ben and Chirkin, Artem and Li, Mingqin and Zhang, Minjia},
        series = {{SIGMOD} '26},
        booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
        publisher = {Association for Computing Machinery},
        doi = {10.1145/3749189},
        url = {https://dl.acm.org/doi/10.1145/3749189},
        year = {2026}
}

Incoming Citations (Sorted by Pagerank)

Showing 3 of 3 citing papers.

Previous Page 1 / 1 Next

Outgoing Citations (Sorted by Pagerank)

Showing 9 of 9 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Previous Page 1 / 1 Next

Semantically Similar Papers