Related papers: Visualization of Extremely Sparse Contingency Tabl…

Transformers' quadratic complexity with respect to the input sequence length has motivated a body of work on efficient sparse approximations to softmax. An alternative path, used by entmax transformers, consists of having built-in exact…

The evolution of large language models (LLMs) towards applications with ultra-long contexts faces challenges posed by the high computational and memory costs of the Transformer architecture. While existing sparse and linear attention…

A bottleneck to developing Semantic Parsing (SP) models is the need for a large volume of human-labeled training data. Given the complexity and cost of human annotation for SP, labeled data is often scarce, particularly in multilingual…

Large spatial datasets often represent a number of spatial point processes generated by distinct entities or classes of events. When crossed with covariates, such as discrete time buckets, this can quickly result in a data set with millions…

Large language models spend most of their inference cost on attention over long contexts, yet empirical behavior suggests that only a small subset of tokens meaningfully contributes to each query. We formalize this phenomenon by modeling…

We present a new dataset for form understanding in noisy scanned documents (FUNSD) that aims at extracting and structuring the textual content of forms. The dataset comprises 199 real, fully annotated, scanned forms. The documents are noisy…

Despite its significance, Arabic, a linguistically rich and morphologically complex language, faces the challenge of being under-resourced. The scarcity of large annotated datasets hampers the development of accurate tools for subjectivity…

With the advancement of deep models, research work on image captioning has led to a remarkable gain in raw performance over the last decade, along with increasing model complexity and computational cost. However, surprisingly works on…

The Maximum Balanced Biclique Problem is a well-known graph model with relevant applications in diverse domains. This paper introduces a novel algorithm, which combines an effective constraint-based tabu search procedure and two dedicated…

We introduce the Text Classification Attack Benchmark (TCAB), a dataset for analyzing, understanding, detecting, and labeling adversarial attacks against text classifiers. TCAB includes 1.5 million attack instances, generated by twelve…

Self-attention has recently been adopted for a wide range of sequence modeling problems. Despite its effectiveness, self-attention suffers from quadratic compute and memory requirements with respect to sequence length. Successful approaches…

Most of the previous methods for table recognition rely on training datasets containing many richly annotated table images. Detailed table image annotation, e.g., cell or text bounding box annotation, however, is costly and often…

This paper describes a technique to compare large text sources using word vector representations (word2vec) and dimensionality reduction (t-SNE) and how it can be implemented using Python. The technique provides a bird's-eye view of text…

Vision-based perception for autonomous driving requires an explicit modeling of a 3D space, where 2D latent representations are mapped and subsequent 3D operators are applied. However, operating on dense latent spaces introduces a cubic…

Recent advances in semantic correspondence have been largely driven by the use of pre-trained large-scale models. However, a limitation of these approaches is their dependence on high-resolution input images to achieve optimal performance,…

Prior works have shown that neural networks can be heavily pruned while preserving performance, but the impact of pruning on model interpretability remains unclear. In this work, we investigate how magnitude-based pruning followed by…

To overcome the data sparsity issue in short text topic modeling, existing methods commonly rely on data augmentation or the data characteristic of short texts to introduce more word co-occurrence information. However, most of them do not…

Projection algorithms such as t-SNE or UMAP are useful for the visualization of high dimensional data, but depend on hyperparameters which must be tuned carefully. Unfortunately, iteratively recomputing projections to find the optimal…

We present encube $-$ a qualitative, quantitative and comparative visualisation and analysis system, with application to high-resolution, immersive three-dimensional environments and desktop displays. encube extends previous comparative…

This paper presents SANA-1.5, a linear Diffusion Transformer for efficient scaling in text-to-image generation. Building upon SANA-1.0, we introduce three key innovations: (1) Efficient Training Scaling: A depth-growth paradigm that enables…