Related papers: CSI-JEPA: Towards Foundation Representations for U…
Ultrasound (US) imaging poses unique challenges for representation learning due to its inherently noisy acquisition process. The low signal-to-noise ratio and stochastic speckle patterns hinder standard self-supervised learning methods…
This paper demonstrates an approach for learning highly semantic image representations without relying on hand-crafted data-augmentations. We introduce the Image-based Joint-Embedding Predictive Architecture (I-JEPA), a non-generative…
Machine learning techniques have shown remarkable accuracy in localization tasks, but their dependency on vast amounts of labeled data, particularly Channel State Information (CSI) and corresponding coordinates, remains a bottleneck.…
Because each indoor site has its own radio propagation characteristics, a site survey process is essential to optimize a Wi-Fi ranging strategy for range-based positioning solutions. This paper studies an unsupervised learning technique…
World models require robust relational understanding to support prediction, reasoning, and control. While object-centric representations provide a useful abstraction, they are not sufficient to capture interaction-dependent dynamics. We…
Accurate channel state information (CSI) underpins reliable and efficient wireless communication. However, acquiring CSI via pilot estimation incurs substantial overhead, especially in massive multiple-input multiple-output (MIMO) systems…
Self-supervised learning has seen great success recently in unsupervised representation learning, enabling breakthroughs in natural language and image processing. However, these methods often rely on autoregressive and masked modeling,…
Joint-Embedding Predictive Architectures (JEPAs) have recently emerged as a novel and powerful technique for self-supervised representation learning. They aim to learn an energy-based model by predicting the latent representation of a…
WiFi sensing has emerged as a compelling contactless modality for human activity monitoring by capturing fine-grained variations in Channel State Information (CSI). Its ability to operate continuously and non-intrusively while preserving…
Learning efficient representations for decision-making policies is a challenge in imitation learning (IL). Current IL methods require expert demonstrations, which are expensive to collect. Additionally, they are not explicitly trained to…
Building upon the foundational work of the Bachelor's Degree Thesis titled "Analysis and Characterization of Wi-Fi Channel State Information'', this thesis significantly advances the research by conducting an in-depth analysis of CSIs,…
Image-based Joint-Embedding Predictive Architecture (IJEPA) offers an attractive alternative to Masked Autoencoder (MAE) for representation learning using the Masked Image Modeling framework. IJEPA drives representations to capture useful…
Invariance-based and generative methods have shown a conspicuous performance for 3D self-supervised representation learning (SSRL). However, the former relies on hand-crafted data augmentations that introduce bias not universally applicable…
The cornerstone of cognitive intelligence lies in extracting hidden patterns from observations and leveraging these principles to systematically predict future outcomes. However, current image tokenization methods demonstrate significant…
Recently, deep learning-enabled joint-source channel coding (JSCC) has received increasing attention due to its great success in image transmission. However, most existing JSCC studies only focus on single-input single-output (SISO)…
Joint Embedding Predictive Architectures (JEPA) have emerged as a powerful framework for learning general-purpose representations. However, these models often lack interpretability and suffer from inefficiencies due to dense embedding…
Channel state information (CSI) is a fundamental component in both wireless communication and sensing systems, enabling critical functions such as radio resource optimization and environmental perception. In wireless sensing, data scarcity…
We present EB-JEPA, an open-source library for learning representations and world models using Joint-Embedding Predictive Architectures (JEPAs). JEPAs learn to predict in representation space rather than pixel space, avoiding the pitfalls…
In this paper, we consider people counting and localization systems exploiting channel state information (CSI) measured from commodity WiFi network interface cards (NICs). While CSI has useful information of amplitude and phase to describe…
Channel prediction permits to acquire channel state information (CSI) without signaling overhead. However, almost all existing channel prediction methods necessitate the deployment of a dedicated model to accommodate a specific…