Cracking Vector Search Indexes
Summary: CrackIVF is a progressive, workload-adaptive partition index for ANNS over cold or unseen data-lake datasets. It answers queries immediately and converges toward conventional index quality, delivering 10–1000× faster initialization. (summarized by gpt-5.6-luna on Jul 24 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Vasilis Mageirakos (ETH Zurich)
- 2. Bowen Wu (ETH Zurich)
- 3. Gustavo Alonso (ETH Zurich)
BibTeX Citation
@article{mageirakos_vldb25,
title = {{Cracking Vector Search Indexes}},
author = {Mageirakos, Vasilis and Wu, Bowen and Alonso, Gustavo},
journal = {PVLDB},
series = {{VLDB} '25},
volume = {18},
number = {11},
pages = {3951--3964},
doi = {10.14778/3749646.3749666},
url = {https://doi.org/10.14778/3749646.3749666},
year = {2025}
}Incoming Citations (Sorted by Pagerank)
Showing 2 of 2 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 10,227 | Efficient Index Layout and Search Strategy for Large-scale High-dimensional Vector Similarity Search | 2026 | SIGMOD | 5.093636e-05 |
| 10,299 | Through the Lens of Hubness: A Revisit on Graph-Based Approximate Nearest Neighbor Search: [Experiments & Analysis] | 2026 | SIGMOD | 5.093636e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 23 of 23 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
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 10,227 | Efficient Index Layout and Search Strategy for Large-scale High-dimensional Vector Similarity Search | 2026 | SIGMOD |
| 2 | 8,872 | Cost-Effective, Low Latency Vector Search with Azure Cosmos DB | 2025 | VLDB |
| 3 | 10,459 | From Prefix Cache to Fusion RAG Cache: Accelerating LLM Inference in Retrieval-Augmented Generation | 2026 | SIGMOD |
| 4 | 259 | Database Cracking | 2007 | CIDR |
| 5 | 10,493 | Reveal Hidden Pitfalls and Navigate Next Generation of Vector Similarity Search from Task-Centric Views: [Experiments & Analysis] | 2026 | SIGMOD |
| 6 | 10,350 | Building Stateless Serverless Vector DBs via Block-based Data Partitioning | 2026 | SIGMOD |
| 7 | 2,816 | Cache-Craft: Managing Chunk-Caches for Efficient Retrieval-Augmented Generation | 2025 | SIGMOD |
| 8 | 9,918 | HAKES: Scalable Vector Database for Embedding Search Service | 2025 | VLDB |
| 9 | 9,778 | Turbocharging Vector Databases using Modern SSDs | 2025 | VLDB |
| 10 | 6,334 | MIRAGE-ANNS: Mixed Approach Graph-based Indexing for Approximate Nearest Neighbor Search | 2025 | SIGMOD |