Deep tabular models have demonstrated remarkable success on i.i.d. data, excelling in a variety of structured data tasks. However, their performance often deteriorates under temporal distribution shifts, where trends and periodic patterns are present in the evolving data distribution over time. In this paper, we explore the underlying reasons for this failure in capturing temporal dependencies. We begin by investigating the training protocol, revealing a key issue in how model selection perform. While existing approaches use temporal ordering for splitting validation set, we show that even a random split can significantly improve model performance. By minimizing the time lag between training data and test time, while reducing the bias in validation, our proposed training protocol significantly improves generalization across various methods. Furthermore, we analyze how temporal data affects deep tabular representations, uncovering that these models often fail to capture crucial periodic and trend information. To address this gap, we introduce a plug-and-play temporal embedding method based on Fourier series expansion to learn and incorporate temporal patterns, offering an adaptive approach to handle temporal shifts. Our experiments demonstrate that this temporal embedding, combined with the improved training protocol, provides a more effective and robust framework for learning from temporal tabular data.

Musculoskeletal injuries during military training significantly impact readiness, making prevention through activity monitoring crucial. While Human Activity Recognition (HAR) using wearable devices offers promising solutions, it faces challenges in processing continuous data streams and recognizing diverse activities without predefined sessions. This paper introduces an end-to-end framework for preprocessing, analyzing, and recognizing activities from wearable data in military training contexts. Using data from 135 soldiers wearing \textit{Garmin--55} smartwatches over six months with over 15 million minutes. We develop a hierarchical deep learning approach that achieves 93.8% accuracy in temporal splits and 83.8% in cross-user evaluation. Our framework addresses missing data through physiologically-informed methods, reducing unknown sleep states from 40.38% to 3.66%. We demonstrate that while longer time windows (45-60 minutes) improve basic state classification, they present trade-offs in detecting fine-grained activities. Additionally, we introduce an intuitive visualization system that enables real-time comparison of individual performance against group metrics across multiple physiological indicators. This approach to activity recognition and performance monitoring provides military trainers with actionable insights for optimizing training programs and preventing injuries.

Social media platforms host discussions about a wide variety of topics that arise everyday. Making sense of all the content and organising it into categories is an arduous task. A common way to deal with this issue is relying on topic modeling, but topics discovered using this technique are difficult to interpret and can differ from corpus to corpus. In this paper, we present a new task based on tweet topic classification and release two associated datasets. Given a wide range of topics covering the most important discussion points in social media, we provide training and testing data from recent time periods that can be used to evaluate tweet classification models. Moreover, we perform a quantitative evaluation and analysis of current general- and domain-specific language models on the task, which provide more insights on the challenges and nature of the task.