VecDB@ICML2025

News

July 11, 2025: Added detailed instructions for authors.
July 10, 2025: Updated the shedule.
July 7, 2025: All papers are now available on OpenReview.
June 20, 2025: Accepted papers are now available on the Accepted Papers page.
June 20, 2025: The schedule has been updated.

Introduction

Vector databases (Vector DBs) are a foundational and critical application layer for injecting information into large language models (LLMs). Although different companies have proposed various vector databases, no academic workshop has previously existed to discuss these systems comprehensively. This workshop aims to foster discussions on vector databases from various perspectives, ranging from mathematical theories to implementation-level optimizations. Topics covered in the workshop include retrieval-augmented generation (RAG), algorithms and data structures for approximate nearest neighbor search (ANN), 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

Location: Vancouver Convention Centre, Vancouver, Canada
Date: July 18, 2025
Room: West Building, Level 2, Meeting Room 208-209
Hybrid: Keynotes and oral presentations will be live-streamed. Registration required to access the stream.

Time	Event
8:30 AM -- 8:40 AM	Opening Remarks
8:40 AM -- 9:25 AM	Keynote 1: Matthijs Douze (Meta) (Chair: Yusuke Matsui) Vector search for machine learning and machine learning for vector search ☯
9:30 AM -- 10:30 AM	Oral Session 1 (Chair: Harsha Vardhan Simhadri) A Bi-metric Framework for Efficient Nearest Neighbor Search, Haike Xu, Piotr Indyk, Sandeep Silwal The RaBitQ Library, Jianyang Gao, Yutong Gou, Yuexuan Xu, Jifan Shi, Zhonghao Yang, Cheng Long IVF\(^{2}\) Index: Fusing Classic and Spatial Inverted Indices for Fast Filtered ANNS, Ben Landrum, Magdalen Dobson Manohar, Mazin Karjikar, Laxman Dhulipala
10:30 AM -- 12:00 PM	Poster Session 1 A Bi-metric Framework for Efficient Nearest Neighbor Search, Haike Xu, Piotr Indyk, Sandeep Silwal The RaBitQ Library, Jianyang Gao, Yutong Gou, Yuexuan Xu, Jifan Shi, Zhonghao Yang, Cheng Long IVF\(^{2}\) Index: Fusing Classic and Spatial Inverted Indices for Fast Filtered ANNS, Ben Landrum, Magdalen Dobson Manohar, Mazin Karjikar, Laxman Dhulipala Unified Multimodal Interleaved Document Representation for Retrieval, Jaewoo Lee, Joonho Ko, Jinheon Baek, Soyeong Jeong, Sung Ju Hwang DistributedANN: Efficient Scaling of a Single DiskANN Graph Across Thousands of Computers, Philip Adams, Menghao Li, Shi Zhang, Li Tan, Qi Chen, Mingqin Li, Zengzhong Li, Knut Magne Risvik, Harsha Vardhan simhadri Scalable k-Means Clustering for Large k via Seeded Approximate Nearest-Neighbor Search, Eliot W. Robson, Jack Spalding-Jamieson, Da Wei Zheng FrugalRAG: Learning to retrieve and reason for multi-hop QA, Abhinav Java, Srivathsan Koundinyan, Nagarajan Natarajan, Amit Sharma Don't Lag, RAG: Training-Free Adversarial Detection Using RAG, Roie Kazoom, Raz Lapid, Moshe Sipper, Ofer Hadar ConvSearch-R1: Enhancing Query Reformulation for Conversational Search with Reasoning via Reinforcement Learning, Changtai Zhu, Siyin Wang, Ruijun Feng, Kai Song, Xipeng Qiu Graph-Based Vector Search: An Experimental Evaluation of the State-of-the-Art, Ilias Azizi, Karima Echihabi, Themis Palpanas, Vassilis Christophides
12:00 PM -- 1:00 PM	Lunch
1:00 PM -- 1:45 PM	Keynote 2: Hiroyuki Ootomo (NVIDIA) (Chair: Harsha Vardhan Simhadri) GPU-oriented High-Performance Graph-based Approximate Nearest Neighbor Search
1:45 PM -- 3:00 PM	Poster Session 2 \( \alpha \)-Reachable Graphs for Multi-vector Nearest Neighbor Search, Siddharth Gollapudi, Ravishankar Krishnaswamy, Ben Landrum, Nikhil Rao, Kirankumar Shiragur, Sandeep Silwal, Harsh Wardhan Enhancing Retrieval Systems with Inference-Time Logical Reasoning, Felix Faltings, Wei Wei, Yujia Bao Down with the Hierarchy: The 'H' in HNSW Stands for "Hubs", Munyampirwa, Vihan Lakshman, Benjamin Coleman Accurate and Efficient Metadata Filtering in Pinecone's Serverless Vector Database, Amir Ingber, Edo Liberty Vector Data Search with Sorting Transformation, Hongzhi Wang, Tanveer F Syeda-Mahmood Rewrite-to-Rank: Optimizing Ad Visibility via Retrieval-Aware Text Rewriting, Chloe Ho, Ishneet Sukhvinder Singh, Diya Sharma, Tanvi Reddy Anumandla, Kevin Zhu, Michael Lu, Vasu Sharma Entropy-Based Dynamic Hybrid Retrieval for Adaptive Query Weighting in RAG Pipelines, John Richard Perez, James Yuncheng Zhou, Radley Le, Alexander Menchtchikov, Ryan Lagasse Exploiting Sparsity for Long Context Inference: Million Token Contexts on Commodity GPUs, Ryan Synk, Monte Hoover, John Kirchenbauer, Neel Jain, Alex Stein, Manli Shu, Josue Melendez Sanchez, Ramani Duraiswami, Tom Goldstein Scaling Laws for Nearest Neighbor Search, Philip Sun, Felix Chern, Yaroslav Akhremtsev, Ruiqi Guo, David Simcha, Sanjiv Kumar LEANN: A Low-Storage Vector Index for Personal Devices, Yichuan Wang, Shu Liu, Zhifei Li, Yongji Wu, Ziming Mao, Yilong Zhao, Xiao Yan, Zhiying Xu, Yang Zhou, Ion Stoica, Sewon Min, Matei Zaharia, Joseph E. Gonzalez Learning Filter-Aware Distance Metrics for Nearest Neighbor Search with Multiple Filters, Gopal R Srinivasa, Ananya Sutradhar, Suryansh Gupta, Ravishankar Krishnaswamy, Kirankumar Shiragur
3:00 PM -- 3:30 PM	Coffee Break
3:30 PM -- 4:15 PM	Keynote 3: Prashant Pandey (Northeastern University) (Chair: Magdalen Dobson Manohar) Vector Search for Large-Scale Genomic Discovery
4:15 PM -- 5:15 PM	Oral Session 2 (Chair: Magdalen Dobson Manohar) \( \alpha \)-Reachable Graphs for Multi-vector Nearest Neighbor Search, Siddharth Gollapudi, Ravishankar Krishnaswamy, Ben Landrum, Nikhil Rao, Kirankumar Shiragur, Sandeep Silwal, Harsh Wardhan Enhancing Retrieval Systems with Inference-Time Logical Reasoning, Felix Faltings, Wei Wei, Yujia Bao Down with the Hierarchy: The 'H' in HNSW Stands for "Hubs", Munyampirwa, Vihan Lakshman, Benjamin Coleman
5:15 PM -- 5:30 PM	Closing Remarks

Speakers

Organizers

Program committee

Matteo Ceccarello, University of Padova
Hiroyuki Deguchi, NTT
Ryota Hinami, Mantra Inc.
Ravishankar Krishnaswamy, Microsoft Research
Yu-Chieh Lin, Kioxia Corporation
Youyang Ng, Kioxia Corporatoin
Yuji Nozawa, Kioxia Corporation
Ninh Pham, University of Auckland
Rahul Raja, LinkedIn
Tobias Rubel, University of Maryland
Kirankumar Shiragur, Microsoft Research
Yusuke Uchida, GO Inc.
Arpita Vats, Santa Clara University

Contact

vecdb-ws-icml2025@googlegroups.com