Related papers: Time-Series JEPA for Predictive Remote Control und…

Building deep learning models that can reason about their environment requires capturing its underlying dynamics. Joint-Embedded Predictive Architectures (JEPA) provide a promising framework to model such dynamics by learning…

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,…

Predicting satellite imagery requires a balance between structural accuracy and textural detail. Standard deterministic methods like PredRNN or SimVP minimize pixel-based errors but suffer from the "regression to the mean" problem,…

Recent advances in machine learning (ML) have shown promise in accelerating the discovery of polymers with desired properties by aiding in tasks such as virtual screening via property prediction. However, progress in polymer ML is hampered…

The interconnected smart devices and industrial internet of things devices require low-latency communication to fulfill control objectives despite limited resources. In essence, such devices have a time-critical nature but also require a…

We propose a simple timed broadcasting process calculus for modelling wireless network protocols. The operational semantics of our calculus is given in terms of a labelled transition semantics which is used to derive a standard (weak)…

This paper addresses the real-time energy dispatch of a hybrid system comprising cascaded hydropower plants, wind, and solar units, jointly participating in the day-ahead energy market under inflow, renewable generation, and price…

Many common methods for learning a world model for pixel-based environments use generative architectures trained with pixel-level reconstruction objectives. Recently proposed Joint Embedding Predictive Architectures (JEPA) offer a…

We introduce a self-supervised framework for learning predictive and structured representations of wireless channels by modeling the temporal evolution of channel state information (CSI) in a compact latent space. Our method casts the…

We introduce a two-stage self-supervised framework that combines the Joint-Embedding Predictive Architecture (JEPA) with a Density Adaptive Attention Mechanism (DAAM) for learning robust speech representations. Stage~1 uses JEPA with DAAM…

Time-Sensitive Networking (TSN) extends IEEE 802.1 Ethernet for safety-critical and real-time applications in several areas, e.g., automotive, aerospace or industrial automation. However, many of these systems also have stringent security…

Semi-supervised learning has emerged as a powerful paradigm for leveraging large amounts of unlabeled data to improve the performance of machine learning models when labeled data are scarce. Among existing approaches, methods derived from…

Joint Embedding Predictive Architectures (JEPAs) learn representations able to solve numerous downstream tasks out-of-the-box. JEPAs combine two objectives: (i) a latent-space prediction term, i.e., the representation of a slightly…

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…

In moderate- to high-mobility scenarios, CSI varies rapidly and becomes temporally non-stationary, leading to severe performance degradation in the massive MIMO transmissions. To address this issue, we propose a tensor-structured approach…

Robotic imitation learning is often treated as reproducing demonstrated actions, but actions are inherently embodiment-specific. When demonstrations come from humans or robots with different morphology, kinematics, or action spaces, this…

Graph Neural Networks (GNNs) have shown promise in learning dynamic functional connectivity for distinguishing phenotypes from human brain networks. However, obtaining extensive labeled clinical data for training is often…

In power electronic systems (PES), attacks on data availability such as latency attacks, data dropouts, and time-synchronization attacks (TSAs) continue to pose significant threats to both the communication network and the control system…

In the upcoming industrial internet of things (IIoT) era, a surge of task-oriented applications will rely on real-time wireless control systems (WCSs). For these systems, ultra-reliable and low-latency wireless communication will be crucial…

The coordination of robotic swarms and the remote wireless control of industrial systems are among the major use cases for 5G and beyond systems: in these cases, the massive amounts of sensory information that needs to be shared over the…