Related papers: PI-JEPA: Label-Free Surrogate Pretraining for Coup…

Dataset pruning reduces the storage and training costs of deep learning by selecting an informative subset from a large dataset. However, most existing pruning methods require fully labeled data, which limits their applicability in…

Constraint-based learning reduces the burden of collecting labels by having users specify general properties of structured outputs, such as constraints imposed by physical laws. We propose a novel framework for simultaneously learning these…

Reliable multiscale models of thrombosis require platelet-scale fidelity at organ-scale cost, a gap that scientific machine learning has the potential to narrow. We train a DeepONet surrogate on platelet dynamics generated with LAMMPS for…

Modelling complex multiphysics systems governed by nonlinear and strongly coupled partial differential equations (PDEs) is a cornerstone in computational science and engineering. However, it remains a formidable challenge for traditional…

Accurate modeling of scrape-off layer (SOL) and divertor-edge dynamics is vital for designing plasma-facing components in fusion devices. High-fidelity edge fluid/neutral codes such as SOLPS-ITER capture SOL physics with high accuracy, but…

The unsupervised pretraining of object detectors has recently become a key component of object detector training, as it leads to improved performance and faster convergence during the supervised fine-tuning stage. Existing unsupervised…

Learning audio representations from raw waveforms overcomes key limitations of spectrogram-based audio representation learning, such as the long latency of spectrogram computation and the loss of phase information. Yet, while…

This paper explores the automated process of determining stem compatibility by identifying audio recordings of single instruments that blend well with a given musical context. To tackle this challenge, we present Stem-JEPA, a novel…

Recent vision-language-action (VLA) models built upon pretrained vision-language models (VLMs) have achieved significant improvements in robotic manipulation. However, current VLAs still suffer from low sample efficiency and limited…

Joint-Embedding Predictive Architectures (JEPAs), a powerful class of self-supervised models, exhibit an unexplained ability to cluster time-series data by their underlying dynamical regimes. We propose a novel theoretical explanation for…

Electroencephalography (EEG) is a widely used tool for studying brain function, with applications in clinical neuroscience, diagnosis, and brain-computer interfaces (BCIs). Recent EEG foundation models trained on large unlabeled corpora aim…

Parametric PDEs power modern simulation, design, and digital-twin systems, yet their many-query workloads still hinge on repeatedly solving large finite-element systems. Existing operator-learning approaches accelerate this process but…

Damage identification is a core task in structural health monitoring. In practice, however, its reliability is often compromised by confounding non-damage effects, such as variations in excitation and environmental conditions, which can…

Semi-supervised classification is a great focus of interest, as in real-world scenarios obtaining labels is expensive, time-consuming and might require expert knowledge. This has motivated the fast development of semi-supervised techniques,…

In recent years, semi-supervised learning (SSL) has shown tremendous success in leveraging unlabeled data to improve the performance of deep learning models, which significantly reduces the demand for large amounts of labeled data. Many SSL…

The needs for precisely estimating a student's academic performance have been emphasized with an increasing amount of attention paid to Intelligent Tutoring System (ITS). However, since labels for academic performance, such as test scores,…

Pre-trained language models derive substantial linguistic and factual knowledge from the massive corpora on which they are trained, and prompt engineering seeks to align these models to specific tasks. Unfortunately, existing prompt…

With the advent of Joint Embedding Predictive Architectures (JEPAs), which appear to be more capable than reconstruction-based methods, this paper introduces a novel technique for creating world models using continuous-time dynamic systems…

Task engagement is defined as loadings on energetic arousal (affect), task motivation, and concentration (cognition). It is usually challenging and expensive to label cognitive state data, and traditional computational models trained with…

Current multimodal learning strategies primarily optimize in the original token space. Such a framework is easy to incorporate with the backbone of pretrained language model, but might result in modality collapse. To alleviate such issues,…