Related papers: Top-P Masking for Cross Language Information Retri…

Large web-sourced multimodal datasets have powered a slew of new methods for learning general-purpose visual representations, advancing the state of the art in computer vision and revolutionizing zero- and few-shot recognition. One crucial…

Information Retrieval (IR) methods aim to identify documents relevant to a query, which have been widely applied in various natural language tasks. However, existing approaches typically consider only the textual content within documents,…

Sequential pattern mining (SPM) has excellent prospects and application spaces and has been widely used in different fields. The non-overlapping SPM, as one of the data mining techniques, has been used to discover patterns that have…

Several advances have been made recently towards handling overlapping speech for speaker diarization. Since speech and natural language tasks often benefit from ensemble techniques, we propose an algorithm for combining outputs from such…

Despite the remarkable ability of large language models (LMs) to comprehend and generate language, they have a tendency to hallucinate and create factually inaccurate output. Augmenting LMs by retrieving information from external knowledge…

Over the past few years, as large language models have ushered in an era of intelligence emergence, there has been an intensified focus on scaling networks. Currently, many network architectures are designed manually, often resulting in…

The objective in this paper is to improve the performance of text-to-image retrieval. To this end, we introduce a new framework that can boost the performance of large-scale pre-trained vision-language models, so that they can be used for…

Masked diffusion models have demonstrated competitive results on various tasks including language generation. However, due to its iterative refinement process, the inference is often bottlenecked by slow and static sampling speed. To…

Dense retrieval models usually adopt vectors from the last hidden layer of the document encoder to represent a document, which is in contrast to the fact that representations in different layers of a pre-trained language model usually…

This paper proposes a dual skipping guidance scheme with hybrid scoring to accelerate document retrieval that uses learned sparse representations while still delivering a good relevance. This scheme uses both lexical BM25 and learned neural…

Image Splicing Localization (ISL) is a fundamental yet challenging task in digital forensics. Although current approaches have achieved promising performance, the edge information is insufficiently exploited, resulting in poor integrality…

In this paper, we study the cross-modal image retrieval, where the inputs contain a source image plus some text that describes certain modifications to this image and the desired image. Prior work usually uses a three-stage strategy to…

Keyword-based web queries with local intent retrieve web content that is relevant to supplied keywords and that represent points of interest that are near the query location. Two broad categories of such queries exist. The first encompasses…

Transformer models have established new benchmarks in natural language processing; however, their increasing depth results in substantial growth in parameter counts. While existing recurrent transformer methods address this issue by…

Image-language learning has made unprecedented progress in visual understanding. These developments have come at high costs, as contemporary vision-language models require large model scales and amounts of data. We here propose a much…

We present TopClustRAG, a retrieval-augmented generation (RAG) system developed for the LiveRAG Challenge, which evaluates end-to-end question answering over large-scale web corpora. Our system employs a hybrid retrieval strategy combining…

Mixed Integer Linear Programming (MILP) is a fundamental class of NP-hard problems that has garnered significant attention from both academia and industry. The Branch-and-Bound (B\&B) method is the dominant approach for solving MILPs and…

Despite their importance in model sampling, efficient implementation of Top-k and Top-p algorithms for large vocabularies remains a significant challenge. Existing approaches often rely on sorting, which incurs significant computation and…

Cross-document relation extraction (RE) aims to identify relations between the head and tail entities located in different documents. Existing approaches typically adopt the paradigm of ``\textit{Small Language Model (SLM) + Classifier}''.…

CLIP has shown impressive results in aligning images and texts at scale. However, its ability to capture detailed visual features remains limited because CLIP matches images and texts at a global level. To address this issue, we propose…