Student engagement is crucial for improving learning outcomes in group activities. Highly engaged students perform better both individually and contribute to overall group success. However, most existing automated engagement recognition methods are designed for online classrooms or estimate engagement at the individual level. Addressing this gap, we propose DualEngage, a novel two-stream framework for group-level engagement recognition from in-classroom videos. It models engagement as a joint function of both individual and group-level behaviors. The primary stream models person-level […]

Ver mais

arXiv:2602.21312v1 Announce Type: new Abstract: This work considers a number of optimization problems and reductive relations between them. The two main problems we are interested in are the emph{Optimal Decision Tree} and emph{Set Cover}. We study these two fundamental tasks under precedence constraints, that is, if a test (or set) $X$ is a predecessor of $Y$, then in any feasible decision tree $X$ needs to be an ancestor of $Y$ (or respectively, if $Y$ is added to set […]

Ver mais

People think that becoming a writer is easy. In some ways, it is. All you need is a pen and paper or a computer, an idea, and the determination to write. Voila, you’re a writer now. Writing is easy; becoming serious about your writing is a whole lot harder and more complex. However, why should it be? Writers should be helping each other navigate this crazy world whenever possible. So, if you’re reading this right now, then that […]

Ver mais

arXiv:2603.05574v1 Announce Type: new Abstract: This paper presents PRISM: an instruction-conditioned refinement method for imitation policies in robotic manipulation. This approach bridges Imitation Learning (IL) and Reinforcement Learning (RL) frameworks into a seamless pipeline, such that an imitation policy on a broad generic task, generated from a set of user-guided demonstrations, can be refined through reinforcement to generate new unseen fine-grain behaviours. The refinement process follows the Eureka paradigm, where reward functions for RL are iteratively generated from […]

Ver mais

We love to anthropomorphize our tools. When a Large Language Model produces a brilliant piece of system architecture or a perfectly structured product requirement document, it is tempting to pause and wonder: Is the machine actually thinking? The philosophical counterpunch is well-rehearsed. Aren’t humans just advanced prediction engines? Aren’t we drawing on our own training data, memories and experiences, to guess what we should do or say next, perhaps just running on a noisier temperature setting? It is […]

Ver mais

Across the financial technology sector, large institutions are facing a hard reality. Systems that were built decades ago for stability and control are now under pressure to deliver flexibility, cost efficiency, and faster change. Banks and market infrastructure firms continue to depend on legacy data centers to process sensitive trade data, where outages and errors are not an option. Yet rising operational costs and growing demand for agility have made cloud adoption less of a future goal and […]

Ver mais

arXiv:2604.14163v1 Announce Type: new Abstract: Maritime distress communications transmitted over very high frequency (VHF) radio are safety-critical voice messages used to report emergencies at sea. Under the Global Maritime Distress and Safety System (GMDSS), such messages follow standardized procedures and are expected to convey essential details, including vessel identity, position, nature of the distress, and required assistance. In practice, however, automatic analysis remains difficult because distress messages are often brief, noisy, and produced under stress, may deviate from […]

Ver mais

arXiv:2602.06183v1 Announce Type: new Abstract: Trainings of Large Language Models are generally bottlenecked by matrix multiplications. In the Transformer architecture, a large portion of these operations happens in the Feed Forward Network (FFN), and this portion increases for larger models, up to 50% of the total pretraining floating point operations. We show that we can leverage hardware-accelerated sparsity to accelerate all matrix multiplications in the FFN, with 2:4 sparsity for weights and v:n:m (Venom) sparsity for activations. Our […]

Ver mais

We introduce a lightweight experimentation pipeline designed to lower the barrier for applying machine learning (ML) methods for classifying images in ecological research. We enable ecologists to experiment with ML models independently, thus they can move beyond off-the-shelf models and generate insights tailored to local datasets and specific classification tasks and target variables. Our tool combines a simple command-line interface for preprocessing, training, and evaluation with a graphical interface for annotation, error analysis, and model comparison. This design […]

Ver mais