Multi-stage ranking pipelines have been a practical solution in modern search systems,
where the first-stage retrieval is to return a subset of candidate documents and latter stages …

This paper provides an extensive and thorough overview of the models and techniques
utilized in the first and second stages of the typical information retrieval processing chain …

State-of-the-art visual perception models for a wide range of tasks rely on supervised
pretraining. ImageNet classification is the de facto pretraining task for these models. Yet …

Recently, the generality of natural language text has been leveraged to develop transferable
recommender systems. The basic idea is to employ pre-trained language models (PLM) to …

Quantization based techniques are the current state-of-the-art for scaling maximum inner
product search to massive databases. Traditional approaches to quantization aim to …

Similarity search finds application in database systems handling complex data such as
images or videos, which are typically represented by high-dimensional features and require …

Recently, there has been a pressing need to manage high-dimensional vector data in data
science and AI applications. This trend is fueled by the proliferation of unstructured data and …

Existing language models (LMs) predict tokens with a softmax over a finite vocabulary,
which can make it difficult to predict rare tokens or phrases. We introduce NPM, the first …

Manga (Japanese comics) are popular worldwide. However, current e-manga archives offer
very limited search support, ie, keyword-based search by title or author. To make the manga …

This paper aims to accelerate the test-time computation of convolutional neural networks
(CNNs), especially very deep CNNs that have substantially impacted the computer vision …