Related papers: Jointly Optimizing Query Encoder and Product Quant…

Information retrieval involves selecting artifacts from a corpus that are most relevant to a given search query. The flavor of retrieval typically used in classical applications can be termed as homogeneous and relaxed, where queries and…

We consider the problem of deep neural net compression by quantization: given a large, reference net, we want to quantize its real-valued weights using a codebook with $K$ entries so that the training loss of the quantized net is minimal.…

Deep reinforcement learning (DRL) has achieved remarkable success across various domains, such as video games, robotics, and, recently, large language models. However, the computational costs and memory requirements of DRL models often…

Knowledge-intensive tasks, particularly open-domain question answering (ODQA), document reranking, and retrieval-augmented language modeling, require a balance between retrieval accuracy and generative flexibility. Traditional retrieval…

While extensive research on query evaluation has achieved consistent improvements in the time complexity of algorithms, the space complexity of query evaluation has been largely ignored. This is a particular challenge in settings with…

With the advent of large language models (LLMs), numerous Post-Training Quantization (PTQ) strategies have been proposed to alleviate deployment barriers created by their enormous parameter counts. Quantization achieves compression by…

Neural receivers have shown outstanding performance compared to the conventional ones but this comes with a high network complexity leading to a heavy computational cost. This poses significant challenges in their deployment on…

Recent reasoning-focused language models achieve high accuracy by generating lengthy intermediate reasoning paths before producing final answers. While this approach is effective in solving problems that require logical thinking, long…

Compression of documents, images, audios and videos have been traditionally practiced to increase the efficiency of data storage and transfer. However, in order to process or carry out any analytical computations, decompression has become…

Rate-Distortion Optimized Quantization (RDOQ) has played an important role in the coding performance of recent video compression standards such as H.264/AVC, H.265/HEVC, VP9 and AV1. This scheme yields significant reductions in bit-rate at…

A large item catalogue is a major challenge for deploying modern sequential recommender models, since it makes the memory footprint of the model large and increases inference latency. One promising approach to address this is RecJPQ, which…

Text-to-Video Retrieval (TVR) is essential in video platforms. Dense retrieval with dual-modality encoders leads in accuracy, but its computation and storage scale poorly with corpus size. Thus, real-time large-scale applications adopt…

Recently, retrieval systems based on dense representations have led to important improvements in open-domain question answering, and related tasks. While very effective, this approach is also memory intensive, as the dense vectors for the…

Recently, significant progress has been made in developing reasoning-capable Large Language Models (LLMs) through long Chain-of-Thought (CoT) techniques. However, this long-CoT reasoning process imposes substantial memory overhead due to…

Embedding-based retrieval (EBR) methods are widely used in modern recommender systems thanks to its simplicity and effectiveness. However, along the journey of deploying and iterating on EBR in production, we still identify some fundamental…

Deep learning models have achieved tremendous success in most of the industries in recent years. The evolution of these models has also led to an increase in the model size and energy requirement, making it difficult to deploy in production…

An important goal of online platforms is to enable content discovery, i.e. allow users to find a catalog entity they were not familiar with. A pre-requisite to discover an entity, e.g. a book, with a search engine is that the entity is…

Lossy image compression is pervasively conducted to save communication bandwidth, resulting in undesirable compression artifacts. Recently, extensive approaches have been proposed to reduce image compression artifacts at the decoder side;…

Transformer-based document cross-encoder rerankers are a central component of modern information retrieval systems. Despite their success, these models suffer from high computational costs due to processing long query-document sequences at…

In spite of the great potential of large language models (LLMs) across various tasks, their deployment on resource-constrained devices remains challenging due to their excessive computational and memory demands. Quantization has emerged as…