相关论文: SciPostLayoutTree: A Dataset for Structural Analys…

Learned representations of scientific documents can serve as valuable input features for downstream tasks without further fine-tuning. However, existing benchmarks for evaluating these representations fail to capture the diversity of…

LLMs exhibit advanced reasoning capabilities, offering the potential to transform natural language questions into mathematical models. However, existing open-source datasets in operations research domain lack detailed annotations of the…

Tabular data in digital documents is widely used to express compact and important information for readers. However, it is challenging to parse tables from unstructured digital documents, such as PDFs and images, into machine-readable format…

In the real world, many topics are inter-correlated, making it challenging to investigate their structure and relationships. Understanding the interplay between topics and their relevance can provide valuable insights for researchers,…

Multi-modal information retrieval (MMIR) is a rapidly evolving field, where significant progress, particularly in image-text pairing, has been made through advanced representation learning and cross-modality alignment research. However,…

Diagrams are common tools for representing complex concepts, relationships and events, often when it would be difficult to portray the same information with natural images. Understanding natural images has been extensively studied in…

We present a novel task and dataset for evaluating the ability of vision and language models to conduct visio-linguistic compositional reasoning, which we call Winoground. Given two images and two captions, the goal is to match them…

Crafting effective captions for figures is important. Readers heavily depend on these captions to grasp the figure's message. However, despite a well-developed set of AI technologies for figures and captions, these have rarely been tested…

For the Bio+Med-Vis Challenge 2024, we propose a visual analytics system as a redesign for the scatter pie chart visualization of cell type proportions of spatial transcriptomics data. Our design uses three linked views: a view of the…

We present a novel approach to visually locate bodies of research within the sciences, both at each moment of time and dynamically. This article describes how this approach fits with other efforts to locally and globally map scientific…

Mathematical researchers, especially those in early-career positions, face critical decisions about topic specialization with limited information about the collaborative environments of different research areas. The aim of this paper is to…

Large language models record impressive performance on many natural language processing tasks. However, their knowledge capacity is limited to the pretraining corpus. Retrieval augmentation offers an effective solution by retrieving context…

GRAFT is a structured multimodal benchmark designed to probe how well LLMs handle instruction following, visual reasoning, and tasks requiring tight visual textual alignment. The dataset is built around programmatically generated charts and…

In this paper, we compose a new task for deep argumentative structure analysis that goes beyond shallow discourse structure analysis. The idea is that argumentative relations can reasonably be represented with a small set of predefined…

With the development of data-centric AI, the focus has shifted from model-driven approaches to improving data quality. Academic literature, as one of the crucial types, is predominantly stored in PDF formats and needs to be parsed into…

Scatterplots are used for a variety of visual analytics tasks, including cluster identification, and the visual encodings used on a scatterplot play a deciding role on the level of visual separation of clusters. For visualization designers,…

Generating aesthetic posters is more challenging than simple design images: it requires not only precise text rendering but also the seamless integration of abstract artistic content, striking layouts, and overall stylistic harmony. To…

Scatterplots are one of the simplest and most commonly-used visualizations for understanding quantitative, multidimensional data. However, since scatterplots only depict two attributes at a time, analysts often need to manually generate and…

Recent advances in methods and techniques enable us to develop an interactive overlay to the global map of science based on aggregated citation relations among the 9,162 journals contained in the Science Citation Index and Social Science…

Computer vision is driven by the many datasets available for training or evaluating novel methods. However, each dataset has a different set of class labels, visual definition of classes, images following a specific distribution, annotation…