Related papers: Constant-Delay Enumeration for Nondeterministic Do…

Sorting is a fundamental algorithmic pre-processing technique which often allows to represent data more compactly and, at the same time, speeds up search queries on it. In this paper, we focus on the well-studied problem of sorting and…

Extracting key information from documents, such as receipts or invoices, and preserving the interested texts to structured data is crucial in the document-intensive streamline processes of office automation in areas that includes but not…

Understanding the structure of complex, nonstationary, high-dimensional time-evolving signals is a central challenge in scientific data analysis. In many domains, such as speech and biomedical signal processing, the ability to learn…

We apply category theory to extract multimodal document structure which leads us to develop information theoretic measures, content summarization and extension, and self-supervised improvement of large pretrained models. We first develop a…

Multi-page Document Visual Question Answering requires reasoning over semantics, layouts, and visual elements in long, visually dense documents. Existing OCR-free methods face a trade-off between capacity and precision: end-to-end models…

Learning from data in the presence of outliers is a fundamental problem in statistics. Until recently, no computationally efficient algorithms were known to compute the mean of a high dimensional distribution under natural assumptions in…

This paper proposes two nonlinear dynamics to solve constrained distributed optimization problem for resource allocation over a multi-agent network. In this setup, coupling constraint refers to resource-demand balance which is preserved at…

A conditional sampling oracle for a probability distribution D returns samples from the conditional distribution of D restricted to a specified subset of the domain. A recent line of work (Chakraborty et al. 2013 and Cannone et al. 2014)…

Learning interpretable and disentangled representations of data is a key topic in machine learning research. Variational Autoencoder (VAE) is a scalable method for learning directed latent variable models of complex data. It employs a clear…

We consider the problem of low-rank approximation of massive dense non-negative tensor data, for example to discover latent patterns in video and imaging applications. As the size of data sets grows, single workstations are hitting…

Processing large amounts of data is an essential problem of the big data era. Most of the data exchange is done via direct communication (using APIs) and well-structured file formats (JSON, XML, EDI, etc.), but a significant portion of the…

We present new results on the classical algorithm of variable elimination, which underlies many algorithms including for probabilistic inference. The results relate to exploiting functional dependencies, allowing one to perform inference…

Data-driven reduced-order models based on autoencoders generally lack interpretability compared to classical methods such as the proper orthogonal decomposition. More interpretability can be gained by disentangling the latent variables and…

Document-level Relation Extraction (DocRE) aims to identify relationships between entity pairs within a document. However, most existing methods assume a uniform label distribution, resulting in suboptimal performance on real-world,…

Recently, a new paradigm called Differentiable Search Index (DSI) has been proposed for document retrieval, wherein a sequence-to-sequence model is learned to directly map queries to relevant document identifiers. The key idea behind DSI is…

The use of well-disentangled representations offers many advantages for downstream tasks, e.g. an increased sample efficiency, or better interpretability. However, the quality of disentangled interpretations is often highly dependent on the…

One of the fundamental representation learning tasks is unsupervised sequential disentanglement, where latent codes of inputs are decomposed to a single static factor and a sequence of dynamic factors. To extract this latent information,…

String analysis is the problem of reasoning about how strings are manipulated by a program. It has numerous applications including automatic detection of cross-site scripting (XSS). A popular string analysis technique includes symbolic…

Transformer-based rankers have shown state-of-the-art performance. However, their self-attention operation is mostly unable to process long sequences. One of the common approaches to train these rankers is to heuristically select some…

This paper introduces a scheme for data stream processing which is robust to batch duration. Streaming frameworks process streams in batches retrieved at fixed time intervals. In a common setting a pattern recognition algorithm is applied…