The in-memory algorithms for approximate nearest neighbor search (ANNS) have achieved
great success for fast high-recall search, but are extremely expensive when handling very …

Current state-of-the-art approximate nearest neighbor search (ANNS) algorithms generate
indices that must be stored in main memory for high-recall search, which makes them …

Vector quantization is one of the most popular techniques for approximate nearest neighbor
(ANN) search. Over the past decade, many vector quantization methods have been …

The semantic capabilities of language models (LMs) have the potential to enable rich
analytics and reasoning over vast knowledge corpora. Unfortunately, existing systems lack …

Approximate similarity queries on high-dimensional vector indices have become the
cornerstone for many critical online services. An increasing need for more sophisticated …

Applications increasingly leverage mixed-modality data, and must jointly search over vector
data, such as embedded images, text and video, as well as structured data, such as …

Approximate nearest neighbor (ANN) searching is a fundamental problem in computer
science with numerous applications in (eg,) machine learning and data mining. Recent …

Approximate Nearest Neighbor Search (ANNS) on high dimensional vector data is now
widely used in various applications, including information retrieval, question answering, and …

Approximate nearest neighbor (ANN) search is a fundamental search in multi-dimensional
databases, which has numerous real-world applications, such as image retrieval …

Abstract Deep Metric Learning (DML) proposes to learn metric spaces which encode
semantic similarities as embedding space distances. These spaces should be transferable …