Related papers: Value-guided action planning with JEPA world model…

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…

Navigating to a visually specified goal given natural language instructions remains a fundamental challenge in embodied AI. Existing approaches either rely on reactive policies that struggle with long-horizon planning, or employ world…

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…

Reinforcement learning suffers from limitations in real practices primarily due to the number of required interactions with virtual environments. It results in a challenging problem because we are implausible to obtain a local optimal…

With the advent of Joint Embedding Predictive Architectures (JEPAs), which appear to be more capable than reconstruction-based methods, this paper introduces a novel technique for creating world models using continuous-time dynamic 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) 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…

Joint-embedding predictive architectures (JEPAs) have shown substantial promise in self-supervised representation learning, yet their application in generative modeling remains underexplored. Conversely, diffusion models have demonstrated…

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…

Energy-based predictive world models provide a powerful approach for multi-step visual planning by reasoning over latent energy landscapes rather than generating pixels. However, existing approaches face two major challenges: (i) their…

Joint-Embedding Predictive Architecture (JEPA) is increasingly used for visual representation learning and as a component in model-based RL, but its behavior remains poorly understood. We provide a theoretical characterization of a simple,…

Learning predictive world models from unlabelled video is a foundational challenge in artificial intelligence. While Joint Embedding Predictive Architectures (JEPA) have set new benchmarks in semantic classification, they often remain…

Recent advances in self-supervised visual representation learning have demonstrated the effectiveness of predictive latent-space objectives for learning transferable features. In particular, Image-based Joint-Embedding Predictive…

Current attempts of Reinforcement Learning for Autonomous Controller are data-demanding while the results are under-performed, unstable, and unable to grasp and anchor on the concept of safety, and over-concentrating on noise features due…

Building on the Joint-Embedding Predictive Architecture (JEPA) paradigm, a recent self-supervised learning framework that predicts latent representations of masked regions in high-level feature spaces, we propose Audio-JEPA (Audio…

Joint-Embedding Predictive Architectures (JEPA) are a promising framework for self-supervised video representation learning, yet the behavior of auxiliary objectives in small-scale Video-JEPA training is not well characterized. We report a…

Joint-embedding self-supervised learning (SSL) commonly relies on transformations such as data augmentation and masking to learn visual representations, a task achieved by enforcing invariance or equivariance with respect to these…

We present a transformer architecture-based foundation model for tasks at high-energy particle colliders such as the Large Hadron Collider. We train the model to classify jets using a self-supervised strategy inspired by the Joint Embedding…

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…

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…