Related papers: Self-Supervised Learning from Images with a Joint-…

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…

Accurate diagnosis of heart arrhythmias requires the interpretation of electrocardiograms (ECG), which capture the electrical activity of the heart. Automating this process through machine learning is challenging due to the need for large…

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…

Self-supervised learning of visual representations has been focusing on learning content features, which do not capture object motion or location, and focus on identifying and differentiating objects in images and videos. On the other hand,…

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…

The joint-embedding predictive architecture (JEPA) recently has shown impressive results in extracting visual representations from unlabeled imagery under a masking strategy. However, we reveal its disadvantages, notably its insufficient…

Two competing paradigms exist for self-supervised learning of data representations. Joint Embedding Predictive Architecture (JEPA) is a class of architectures in which semantically similar inputs are encoded into representations that are…

We introduce VL-JEPA, a vision-language model built on a Joint Embedding Predictive Architecture (JEPA). Instead of autoregressively generating tokens as in classical VLMs, VL-JEPA predicts continuous embeddings of the target texts. By…

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…

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 (JEPA) have recently become popular as promising architectures for self-supervised learning. Vision transformers have been trained using JEPA to produce embeddings from images and videos, which have…

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…

Language representation learning has emerged as a promising approach for sequential recommendation, thanks to its ability to learn generalizable representations. However, despite its advantages, this approach still struggles with data…

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…

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…

Trajectory similarity computation is an essential technique for analyzing moving patterns of spatial data across various applications such as traffic management, wildlife tracking, and location-based services. Modern methods often apply…

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…

Recent advancements in self-supervised learning in the point cloud domain have demonstrated significant potential. However, these methods often suffer from drawbacks, including lengthy pre-training time, the necessity of reconstruction in…

This paper explores feature prediction as a stand-alone objective for unsupervised learning from video and introduces V-JEPA, a collection of vision models trained solely using a feature prediction objective, without the use of pretrained…