Related papers: NuTime: Numerically Multi-Scaled Embedding for Lar…

Large, pretrained models are commonly finetuned with imagery that is heavily augmented to mimic different conditions and scales, with the resulting models used for various tasks with imagery from a range of spatial scales. Such models…

There is a recent growing interest in applying Deep Learning techniques to tabular data, in order to replicate the success of other Artificial Intelligence areas in this structured domain. Specifically interesting is the case in which…

Deep learning (DL) has transformed applications in a variety of domains, including computer vision, natural language processing, and tabular data analysis. The search for improved DL model accuracy has led practitioners to explore…

Multivariate time series forecasting requires models to simultaneously capture variable-wise structural dependencies and generalize across diverse tasks. While structural encoders are effective in modeling feature interactions, they lack…

Transformer-based methods have achieved impressive results in time series forecasting. However, existing Transformers still exhibit limitations in sequence modeling as they tend to overemphasize temporal dependencies. This incurs additional…

The ability to learn polynomials and generalize out-of-distribution is essential for simulation metamodels in many disciplines of engineering, where the time step updates are described by polynomials. While feed forward neural networks can…

While multimodal data sources are increasingly available from real-world forecasting, most existing research remains on unimodal time series. In this work, we present MoTime, a suite of multimodal time series forecasting datasets that pair…

Continuous-time models are a natural choice for irregular and asynchronous data. A central design choice is how to embed discrete observations into continuous time. Interpolation- and imputation-based embeddings reconstruct a continuous…

Capitalizing on the need for addressing the existing challenges associated with gesture recognition via sparse multichannel surface Electromyography (sEMG) signals, the paper proposes a novel deep learning model, referred to as the…

Long interaction histories are central to modern recommender systems, yet training with long sequences is often dismissed as impractical under realistic memory and latency budgets. This work demonstrates that it is not only practical but…

Deep learning has made significant advances in creating efficient representations of time series data by automatically identifying complex patterns. However, these approaches lack interpretability, as the time series is transformed into a…

Real-world time series come with text: metadata, descriptions, news, reports. Yet time series foundation models process numerical sequences in isolation, and the multimodal text-and-time-series models that attempt to bridge the two all…

Predictive models play a crucial role in the financial industry, enabling risk prediction, fraud detection, and personalized recommendations, where slight changes in core model performance can result in billions of dollars in revenue or…

An important goal of self-supervised learning is to enable model pre-training to benefit from almost unlimited data. However, one method that has recently become popular, namely masked image modeling (MIM), is suspected to be unable to…

Data-driven models have demonstrated state-of-the-art performance in inferring the temporal ordering of events in text. However, these models often overlook explicit temporal signals, such as dates and time windows. Rule-based methods can…

There is an increasing demand to process streams of temporal data in energy-limited scenarios such as embedded devices, driven by the advancement and expansion of Internet of Things (IoT) and Cyber-Physical Systems (CPS). Spiking neural…

Many prediction problems across science and engineering, especially in finance and economics, involve large cross-sections of individual time series, where each unit (e.g., a loan, stock, or customer) is driven by unit-level features and…

Identifying cell types and subtypes in routine histopathology is fundamental for understanding disease. Existing tile-based models capture nuclear detail but miss the broader tissue context that influences cell identity. Current human…

Traditional spatiotemporal models generally rely on task-specific architectures, which limit their generalizability and scalability across diverse tasks due to domain-specific design requirements. In this paper, we introduce…

Notable progress has been made in generalist medical large language models across various healthcare areas. However, large-scale modeling of in-hospital time series data - such as vital signs, lab results, and treatments in critical care -…