Related papers: LIDER: An Efficient High-dimensional Learned Index…

Name lookup is a key technology for the forwarding plane of content router in Named Data Networking (NDN). To realize the efficient name lookup, what counts is deploying a highperformance index in content routers. So far, the proposed…

Rehearsal approaches enjoy immense popularity with Continual Learning (CL) practitioners. These methods collect samples from previously encountered data distributions in a small memory buffer; subsequently, they repeatedly optimize on the…

Pre-trained language models like BERT have achieved great success in a wide variety of NLP tasks, while the superior performance comes with high demand in computational resources, which hinders the application in low-latency IR systems. We…

Despite the advantages of their low-resource settings, traditional sparse retrievers depend on exact matching approaches between high-dimensional bag-of-words (BoW) representations of both the queries and the collection. As a result,…

Why do even the most powerful 7B-parameter embedding models struggle with simple retrieval tasks that the decades old BM25 handles with ease? Recent theory suggests that this happens because of a dimensionality bottleneck. This occurs when…

Index structures are important for efficient data access, which have been widely used to improve the performance in many in-memory systems. Due to high in-memory overheads, traditional index structures become difficult to process the…

Cross-encoder (CE) models which compute similarity by jointly encoding a query-item pair perform better than embedding-based models (dual-encoders) at estimating query-item relevance. Existing approaches perform k-NN search with CE by…

BERT-based information retrieval models are expensive, in both time (query latency) and computational resources (energy, hardware cost), making many of these models impractical especially under resource constraints. The reliance on a query…

The growth in data storage capacity and the increasing demands for high performance have created several challenges for concurrent indexing structures. One promising solution is learned indexes, which use a learning-based approach to fit…

Embedding index that enables fast approximate nearest neighbor(ANN) search, serves as an indispensable component for state-of-the-art deep retrieval systems. Traditional approaches, often separating the two steps of embedding learning and…

Recent dense retrievers increasingly leverage the robust text understanding capabilities of Large Language Models (LLMs), encoding queries and documents into a shared embedding space for effective retrieval. However, most existing methods…

Minutiae extraction, a fundamental stage in fingerprint recognition, is increasingly shifting toward deep learning. However, truly end-to-end methods that eliminate separate preprocessing and postprocessing steps remain scarce. This paper…

High-dimensional dense embeddings have become central to modern Information Retrieval, but many dimensions are noisy or redundant. Recently proposed DIME (Dimension IMportance Estimation), provides query-dependent scores to identify…

We introduce LADDER (Learning through Autonomous Difficulty-Driven Example Recursion), a framework which enables Large Language Models to autonomously improve their problem-solving capabilities through self-guided learning by recursively…

Dense Retrieval (DR) has achieved state-of-the-art first-stage ranking effectiveness. However, the efficiency of most existing DR models is limited by the large memory cost of storing dense vectors and the time-consuming nearest neighbor…

Dense retrieval systems rank passages by embedding similarity to a query, but multi-hop questions require passages that are associatively related through shared reasoning chains. We introduce Association-Augmented Retrieval (AAR), a…

Deep Neural Networks (DNNs) are witnessing increased adoption in multiple domains owing to their high accuracy in solving real-world problems. However, this high accuracy has been achieved by building deeper networks, posing a fundamental…

We introduce latency-aware network acceleration (LANA) - an approach that builds on neural architecture search techniques and teacher-student distillation to accelerate neural networks. LANA consists of two phases: in the first phase, it…

Approximate nearest neighbour (ANN) search has become a central task in modern data-intensive applications, particularly when operating on large, heterogeneous, or high-dimensional datasets. However, many existing ANN methods struggle in…

We investigate the prospect of reconstructing the ''cosmic distance ladder'' of the Universe using a novel deep learning framework called LADDER - Learning Algorithm for Deep Distance Estimation and Reconstruction. LADDER is trained on the…