Related papers: BiJEPA: Bi-directional Joint Embedding Predictive …

Vision-language pretraining has driven much of the recent progress in medical image representation learning, but this paradigm is constrained by the availability of paired image-text data and by the reporting bias of clinical narratives. We…

Inspired by the success of generative pretraining in natural language, we ask whether the same principles can yield strong self-supervised visual learners. Instead of training models to output features for downstream use, we train them to…

We present V-JEPA 2.1, a family of self-supervised models that learn dense, high-quality visual representations for both images and videos while retaining strong global scene understanding. The approach combines four key components. First,…

Joint-embedding predictive architectures (JEPAs) propose that a model should learn more useful abstractions when trained to predict latent representations rather than observed outputs. For autoregressive language-model fine-tuning the…

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…

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…

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…

Though self-supervised learning (SSL) has demonstrated incredible ability to learn robust representations from unlabeled data, the choice of optimal SSL strategy can lead to vastly different performance outcomes in specialized domains.…

Self-supervised learning (SSL) has made enormous progress and largely narrowed the gap with the supervised ones, where the representation learning is mainly guided by a projection into an embedding space. During the projection, current…

Joint Embedding Self-Supervised Learning (JE-SSL) has seen rapid developments in recent years, due to its promise to effectively leverage large unlabeled data. The development of JE-SSL methods was driven primarily by the search for ever…

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…

Generative models, from diffusion models to large language models, achieve remarkable performance but at a cost in training data orders of magnitude larger than what biological learners require. An alternative paradigm has emerged in which…

World models learned from high-dimensional visual observations allow agents to make decisions and plan directly in latent space, avoiding pixel-level reconstruction. However, recent latent predictive architectures (JEPAs), including the…

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…

A fundamental challenge of bipartite graph representation learning is how to extract informative node embeddings. Self-Supervised Learning (SSL) is a promising paradigm to address this challenge. Most recent bipartite graph SSL methods are…

Self-supervised learning has become an incredibly successful method for feature learning, widely applied to many downstream tasks. It has proven especially effective for discriminative tasks, surpassing the trending generative models.…

Visual Speech Recognition (VSR) tasks are generally recognized to have a lower theoretical performance ceiling than Automatic Speech Recognition (ASR), owing to the inherent limitations of conveying semantic information visually. To…

Self-supervised learning (SSL) has emerged as a powerful paradigm for learning representations without labeled data. Most SSL approaches rely on strong, well-established, handcrafted data augmentations to generate diverse views for…

We study how representation learning can accelerate reinforcement learning from rich observations, such as images, without relying either on domain knowledge or pixel-reconstruction. Our goal is to learn representations that both provide…

We propose WirelessJEPA, a novel wireless foundation model (WFM) that uses the Joint Embedding Predictive Architecture (JEPA). WirelessJEPA learns general-purpose representations directly from real-world multi-antenna IQ data by predicting…