VecDB@VLDB2026

News

August 2, 2026: The full schedule including poster/oral session assignments is now available.
July 23, 2026: The Call for Dataset Announcements has been published with a deadline of August 21, 2026. Please see the Call for Datasets page for details.
July 20, 2026: Camera-ready deadline is extended to July 31, and submission is available in OpenReview.
July 20, 2026: Accepted papers are now available on the Accepted Papers page.
June 12, 2026: The deadline has been extended to Friday, June 19 AoE.
June 2, 2026: The submission site is now open on OpenReview.
May 1, 2026: Submission instructions are now available on the Call for Papers page.
April 12, 2026: Important dates (submission deadline, notification, camera-ready) are now available on the Call for Papers page.
February 3, 2026: Website is now live.

Introduction

Vector databases (Vector DBs) are a foundational and critical application layer for injecting information into large language models (LLMs). Nearly all databases have added support for vector based retrieval and querying. Although various companies have proposed different vector databases, there have been very few academic workshops where these systems are discussed comprehensively. This workshop aims to foster discussions on vector databases from various perspectives, ranging from mathematical theories to implementation-level optimizations and interaction with databases. Topics covered in the workshop include retrieval-augmented generation (RAG), algorithms and data structures for approximate nearest neighbor search (ANN), interaction with databases, data management systems for handling vector data, query languages, and embedding models. Furthermore, the workshop will also function as a platform for companies and researchers working on vector databases to present technical details (white papers) and exchange ideas.

Schedule (Tentative)

Location: The Westin Boston Seaport District, Boston, MA, USA
Date: Friday, September 4, 2026
Room: Grand Ballroom E

Time	Event
8:30-8:45 AM	Intro Remarks
8:45-9:25 AM	Keynote 1
9:25-10:15 AM	Poster Session 1 Almost Navigable Graphs, Pratyush Avi, Christopher Musco Turbocharging PiPNN for Proximity and \(k\)-NN Graph Building, Tobias Rubel, Richard Wen, Guy Blelloch, Laxman Dhulipala, Lars Gottesbüren, Jakub Łącki, Vahab Mirrokni Multi-Vector Embeddings are Provably More Expressive than Single Vector Embeddings, Rajesh Jayaram FastGANN: Marrying Quantization with Pruning for GPU ANNS, ZeAi Sun, Jinxu Liu Can Language Models Actually Retrieve In-Context? Drowning in Documents at Million Token Scale, Siddharth Gollapudi, Nilesh Gupta, Prasann Singhal, Sewon Min Direct Path Optimization for Faster Ingestion and Sparser Graph Index in Vector Database, Tianji Yang, Xuhao Chen Characterizing Locality in Large-Scale Vector Search Workloads of Agentic AI Systems, Seungjin Lee, Faraz Ahmed, Diman Zad Tootaghaj, Hardik Soni, Steven Swanson, Puneet Sharma Learning Partition Trees for Nearest Neighbor Search, Ashwin Padaki, Sanjeev Khanna, Erik Waingarten Metadata-Filtered Vector Search in the WebIQ Grounding Index, Fang Liu, Magdalen Dobson Manohar, Qingcha Chen, Li Tan, Jinwei Zhang, Xinglong He, Denis Deyneko, Son Truong, Arpan Phull, Garrett Kaminaga, Vibhaakar Sharma, Zhaoyi Liu, Zengzhong Li, Knut Magne Risvik Passing the Baton: High Throughput Distributed Disk-Based Vector Search with BatANN, Nam Anh Dang, Ben Landrum, Ken Birman ANNLib: A Development Framework for Efficient Approximate Nearest Neighbor Search, Zheqi Shen, Jingbo Su, Zijin Wan, Yan Gu, Yihan Sun Directional Beam Search: I/O-Efficient ANNS on GPU, Zikun Wang, Hunter McCoy, Prashant Pandey In-Place Updates of a Graph Index for Streaming Approximate Nearest Neighbor Search, Haike Xu, Magdalen Dobson Manohar, Philip A. Bernstein, Badrish Chandramouli, Richard Wen, Harsha Vardhan Simhadri Aggregate Recall Is Not Per-Slice Reliability: A Distribution-Free Coverage Contract for Embedding Retrieval, Rob Sneiderman SPI: Query-Depth-Adaptive Indexing for Streaming RAG in Vector Databases, Dong Liu, Yanxuan Yu, Shinan Liu Mimicking Datasets at Billion Scale for Vector Search Benchmarking, Jinsol Park, Anupam Mijar, Corey J Nolet
10:15-10:45 AM	Coffee Break 1
10:45-11:25 AM	Keynote 2
11:25 AM-12:05 PM	Oral Session 1 Almost Navigable Graphs, Pratyush Avi, Christopher Musco Turbocharging PiPNN for Proximity and \(k\)-NN Graph Building, Tobias Rubel, Richard Wen, Guy Blelloch, Laxman Dhulipala, Lars Gottesbüren, Jakub Łącki, Vahab Mirrokni
12:05-1:45 PM	Lunch
1:45-2:25 PM	Keynote 3
2:25-3:15 PM	Poster Session 2 JAG: Joint Attribute Graphs for Filtered Nearest Neighbor Search, Haike Xu, Guy Blelloch, Laxman Dhulipala, Lars Gottesbüren, Rajesh Jayaram, Jakub Łącki VQ-bench: a composable vector quantization framework, Edo Liberty, Ashwin Padaki, Amir Ingber VIBE: Vector Index Benchmark for Embeddings, Elias Jääsaari, Ville Hyvönen, Matteo Ceccarello, Teemu Roos, Martin Aumüller MV-IVF: Multi-Vector Retrieval via Multi-Vector Clustering, Kishen N Gowda, Laxman Dhulipala, Lars Gottesbüren, Rajesh Jayaram LOCALE: Local-Alignment Embeddings for Noise-Robust DNA Search at SRA Scale, Ryan Synk, Prashant Pandey, S. Cenk Sahinalp, Ramani Duraiswami Quantization Beyond Uniform Bit Allocation, K. S. Sreeramji, Sabyasachi Basu, Ravishankar Krishnaswamy, Kirankumar Shiragur, Yujia Wang DARTH+: Vector Search with Declarative Recall and Guarantees, Manos Chatzakis, Yannis Papakonstantinou, Themis Palpanas Quantizing Sampling-Based Inner Product Sketches, Gabriel M. Silva, Aécio Santos, Majid Daliri, Juliana Freire, Christopher Musco Beyond HyDE: Cross-Model Hypothesis Diversity for Robust Dense Retrieval, Siddhesh More, Kunal Jadhav Revisiting RaBitQ and TurboQuant: A Symmetric Comparison of Methods, Theory, and Experiments, Jianyang Gao, Yutong Gou, Yuexuan Xu, Jifan Shi, Yongyi Yang, Shuolin Li, Raymond Chi-Wing Wong, Cheng Long Plasma: A Layout-Aware Benchmark Reveals Memory Layout Matters for Graph-based ANNS on GPU, Yutaro Oguri, Mai Nishimura, Yusuke Matsui The PAG Library: Projection-Augmented Graph for Approximate Nearest Neighbor Search, Kejing Lu, Zhenpeng Pan, Yoshiharu Ishikawa, Chuan Xiao, Jianbin Qin Speakeasy: Billion-Scale Two-Server Private Semantic Search, Vihan Lakshman, Xiaochen Zhu, Alexandra Henzinger, Henry Corrigan-Gibbs, Emma Dauterman Filtered Approximate Nearest Neighbor Search in Vector Databases: System Design and Performance Analysis, Abylay Amanbayev, Brian Tsan, Tri Vinh Dang, Florin Rusu Range Retrieval with Graph-Based Indices, Magdalen Dobson Manohar, Guy Blelloch, Taekseung Kim Stop Indexing at Full Precision: Revisiting Clustering for Vector Embeddings, Leonardo Kuffo, Peter Boncz
3:15-3:45 PM	Coffee Break 2
3:45-5:05 PM	Oral Session 2 VIBE: Vector Index Benchmark for Embeddings, Elias Jääsaari, Ville Hyvönen, Matteo Ceccarello, Teemu Roos, Martin Aumüller Multi-Vector Embeddings are Provably More Expressive than Single Vector Embeddings, Rajesh Jayaram JAG: Joint Attribute Graphs for Filtered Nearest Neighbor Search, Haike Xu, Guy Blelloch, Laxman Dhulipala, Lars Gottesbüren, Rajesh Jayaram, Jakub Łącki VQ-bench: a composable vector quantization framework, Edo Liberty, Ashwin Padaki, Amir Ingber
5:05-5:15 PM	Wrap up + Discussion
	Dinner (independently)
7:00-9:00 PM	Assemble for drinks

Speakers

Organizers

Program committee

TBD

Past Workshops

The 1st Workshop on Vector Databases (VecDB@ICML2025), July 18, 2025, Vancouver, Canada

Contact

vecdb-ws-vldb2026@googlegroups.com