Related papers: Modeling Layout Reading Order as Ordering Relation…

We introduce "pointer-guided segment ordering" (SO), a novel pre-training technique aimed at enhancing the contextual understanding of paragraph-level text representations in large language models. Our methodology leverages a…

Reduced Order Modelling (ROM) has been widely used to create lower order, computationally inexpensive representations of higher-order dynamical systems. Using these representations, ROMs can efficiently model flow fields while using…

Mobility on Demand (MoD) refers to mobility systems that operate on the basis of immediate travel demand. Typically, such a system consists of a fleet of vehicles that can be booked by customers when needed. The operation of these services…

Visually rich documents (VRDs) challenge retrieval-augmented generation (RAG) with layout-dependent semantics, brittle OCR, and evidence spread across complex figures and structured tables. This survey examines how Multimodal Large Language…

With recent advancements in Large Language Models (LLMs) and growing interest in retrieval-augmented generation (RAG), the ability to understand table structures has become increasingly important. This is especially critical in financial…

Reading text from images or scanned documents via OCR models has been a longstanding focus of researchers. Intuitively, text reading is perceived as a straightforward perceptual task, and existing work primarily focuses on constructing…

In the random-order model for online learning, the sequence of losses is chosen upfront by an adversary and presented to the learner after a random permutation. Any random-order input is \emph{asymptotically} equivalent to a stochastic…

Reduced order models are computationally inexpensive approximations that capture the important dynamical characteristics of large, high-fidelity computer models of physical systems. This paper applies machine learning techniques to improve…

Spatial reasoning is a fundamental aspect of human cognition, enabling intuitive understanding and manipulation of objects in three-dimensional space. While foundation models demonstrate remarkable performance on some benchmarks, they still…

Since their release, Transformers have revolutionized many fields from Natural Language Understanding to Computer Vision. Document Understanding (DU) was not left behind with first Transformer based models for DU dating from late 2019.…

Fine-tuning Large Language Models (LLMs) with first-order methods like back-propagation is computationally intensive. Zeroth-Order (ZO) optimisation uses function evaluations instead of gradients, reducing memory usage, but suffers from…

Large Language Models (LLMs) suffer from order bias, where their performance is affected by the arrangement order of input elements. This unfairness limits the model's applications in scenarios such as in-context learning and…

Reinforcement learning has been applied in operation research and has shown promise in solving large combinatorial optimization problems. However, existing works focus on developing neural network architectures for certain problems. These…

Mathematical morphology provides a nonlinear framework for image and spatial data processing and analysis. Although there have been many successful applications of mathematical morphology to vector-valued images, such as color and…

Ordering has been extensively studied in many visualization applications, such as axis and matrix reordering, for the simple reason that the order will greatly impact the perceived pattern of data. Many quality metrics concerning data…

Machine Reading at Scale (MRS) is a challenging task in which a system is given an input query and is asked to produce a precise output by "reading" information from a large knowledge base. The task has gained popularity with its natural…

When reading a document, glancing at the spatial layout of a document is an initial step to understand it roughly. Traditional document layout analysis (DLA) methods, however, offer only a superficial parsing of documents, focusing on basic…

Recent efforts of multimodal Transformers have improved Visually Rich Document Understanding (VrDU) tasks via incorporating visual and textual information. However, existing approaches mainly focus on fine-grained elements such as words and…

Document layout analysis (DLA) is the task of detecting the distinct, semantic content within a document and correctly classifying these items into an appropriate category (e.g., text, title, figure). DLA pipelines enable users to convert…

When applying learning to rank algorithms to Web search, a large number of features are usually designed to capture the relevance signals. Most of these features are computed based on the extracted textual elements, link analysis, and user…