Related papers: SLIM: Sparsified Late Interaction for Multi-Vector…

BERT based ranking models have achieved superior performance on various information retrieval tasks. However, the large number of parameters and complex self-attention operation come at a significant latency overhead. To remedy this, recent…

Recently developed large pre-trained language models, e.g., BERT, have achieved remarkable performance in many downstream natural language processing applications. These pre-trained language models often contain hundreds of millions of…

One-Shot Federated Learning, where a central server learns a global model in a single communication round, has emerged as a promising paradigm. However, under extremely non-IID settings, existing data-free methods often generate low-quality…

The bi-encoder architecture provides a framework for understanding machine-learned retrieval models based on dense and sparse vector representations. Although these representations capture parametric realizations of the same underlying…

Multi-vector retrieval methods combine the merits of sparse (e.g. BM25) and dense (e.g. DPR) retrievers and have achieved state-of-the-art performance on various retrieval tasks. These methods, however, are orders of magnitude slower and…

We address the recovery of sparse vectors in an overcomplete, linear and noisy multiple measurement framework, where the measurement matrix is known upto a permutation of its rows. We derive sparse Bayesian learning (SBL) based updates for…

Large Language Models (LLMs) have demonstrated success across many benchmarks. However, they still exhibit limitations in long-context scenarios, primarily due to their short effective context length, quadratic computational complexity, and…

Linear mixed models (LMMs), which incorporate fixed and random effects, are key tools for analyzing heterogeneous data, such as in personalized medicine. Nowadays, this type of data is increasingly wide, sometimes containing thousands of…

Behavioral patterns captured in embeddings learned from interaction data are pivotal across various stages of production recommender systems. However, in the initial retrieval stage, practitioners face an inherent tradeoff between embedding…

Multiple instance learning (MIL) is the preferred approach for whole slide image classification. However, most MIL approaches do not exploit the interdependencies of tiles extracted from a whole slide image, which could provide valuable…

We tackle the multi-party speech recovery problem through modeling the acoustic of the reverberant chambers. Our approach exploits structured sparsity models to perform room modeling and speech recovery. We propose a scheme for…

We explore leveraging corpus-specific vocabularies that improve both efficiency and effectiveness of learned sparse retrieval systems. We find that pre-training the underlying BERT model on the target corpus, specifically targeting…

Inspired by recent findings on the fractal geometry of language, we introduce Recursive INference Scaling (RINS) as a complementary, plug-in recipe for scaling inference time in language and multimodal systems. RINS is a particular form of…

In this paper we present an efficient active-set method for the solution of convex quadratic programming problems with general piecewise-linear terms in the objective, with applications to sparse approximations and risk-minimization. The…

A trend in compressed sensing (CS) is to exploit structure for improved reconstruction performance. In the basic CS model, exploiting the clustering structure among nonzero elements in the solution vector has drawn much attention, and many…

Retrieval-augmented generation has proven practical when models require specialized knowledge or access to the latest data. However, existing methods for multimodal document retrieval often replicate techniques developed for text-only…

Visual Language Models require substantial computational resources for inference due to the additional input tokens needed to represent visual information. However, these visual tokens often contain redundant and unimportant information,…

BERT is inefficient for sentence-pair tasks such as clustering or semantic search as it needs to evaluate combinatorially many sentence pairs which is very time-consuming. Sentence BERT (SBERT) attempted to solve this challenge by learning…

Semi-supervised learning (SSL) algorithms have had great success in recent years in limited labeled data regimes. However, the current state-of-the-art SSL algorithms are computationally expensive and entail significant compute time and…

Scoring systems are linear classification models that only require users to add, subtract and multiply a few small numbers in order to make a prediction. These models are in widespread use by the medical community, but are difficult to…