Related papers: Hierarchical JEPA Meets Predictive Remote Control …
The paper introduces a Data-driven Hierarchical Control (DHC) structure to improve performance of systems operating under the effect of system and/or environment uncertainty. The proposed hierarchical approach consists of two parts: 1) A…
Joint Embedding Predictive Architectures (JEPA) are a novel self supervised training technique that have shown recent promise across domains. We introduce BERT-JEPA (BEPA), a training paradigm that adds a JEPA training objective to…
Joint-Embedding Predictive Architecture (JEPA) has emerged as a promising self-supervised approach that learns by leveraging a world model. While previously limited to predicting missing parts of an input, we explore how to generalize the…
Self-supervised learning (SSL) has become an important approach in pretraining large neural networks, enabling unprecedented scaling of model and dataset sizes. While recent advances like I-JEPA have shown promising results for Vision…
We introduce hierarchical neighbor graphs, a new architecture for connecting ad hoc wireless nodes distributed in a plane. The structure has the flavor of hierarchical clustering and requires only local knowledge and minimal computation at…
We propose a hierarchical learning architecture for predictive control in unknown environments. We consider a constrained nonlinear dynamical system and assume the availability of state-input trajectories solving control tasks in different…
Diffusion policies are a powerful paradigm for robot learning, but their training is often inefficient. A key reason is that networks must relearn fundamental spatial concepts, such as translations and rotations, from scratch for every new…
With the advent of technologies such as Edge computing, the horizons of remote computational applications have broadened multidimensionally. Autonomous Unmanned Aerial Vehicle (UAV) mission is a vital application to utilize remote…
Large-scale integration of renewables in power systems gives rise to new challenges for keeping synchronization and frequency stability in volatile and uncertain power flow states. To ensure the safety of operation, the system must maintain…
This paper introduces a novel data-driven hierarchical control scheme for managing a fleet of nonlinear, capacity-constrained autonomous agents in an iterative environment. We propose a control framework consisting of a high-level dynamic…
This work proposes a unified Hierarchical Model Predictive Control (H-MPC) for modular manipulators across various morphologies, as the controller can adapt to different configurations to execute the given task without extensive parameter…
When implementing hierarchical federated learning over wireless networks, scalability assurance and the ability to handle both interference and device data heterogeneity are crucial. This work introduces a new two-level learning method…
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,…
This paper focuses on multimodal alignment within the realm of Artificial Intelligence, particularly in text and image modalities. The semantic gap between the textual and visual modality poses a discrepancy problem towards the…
To achieve efficient long-range wireless power transfer (WPT), large antenna systems are necessary spanning lengths of tens to thousands of meters in one dimension. This creates an array in the order of at least hundreds of thousands to…
This paper presents a hierarchical control scheme for interconnected linear systems. At the higher layer of the control structure a robust centralized Model Predictive Control (MPC) algorithm based on a reduced order dynamic model of the…
The emergence of dense, mission-driven aerial networks supporting the low-altitude economy presents unique communication challenges, including extreme channel dynamics and severe cross-tier interference. Traditional reactive communication…
Building on recent advances in representation learning for wireless channels, this work investigates the cost-benefit trade-offs of high-dimensional channel embeddings in practical systems. We benchmark multiple wireless representations:…
The building thermodynamics model, which predicts real-time indoor temperature changes under potential HVAC (Heating, Ventilation, and Air Conditioning) control operations, is crucial for optimizing HVAC control in buildings. While…
Modern Text-to-Image (T2I) generation increasingly relies on token-centric architectures that are trained with self-supervision, yet effectively fusing text with visual tokens remains a challenge. We propose \textbf{JEPA-T}, a unified…