相关论文: DMT-JEPA: Discriminative Masked Targets for Joint-…

Learning manipulable representations of the world and its dynamics is central to AI. Joint-Embedding Predictive Architectures (JEPAs) offer a promising blueprint, but lack of practical guidance and theory has led to ad-hoc R&D. We present a…

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…

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…

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…

Building deep learning models that can reason about their environment requires capturing its underlying dynamics. Joint-Embedded Predictive Architectures (JEPA) provide a promising framework to model such dynamics by learning…

Recent advances in machine learning (ML) have shown promise in accelerating the discovery of polymers with desired properties by aiding in tasks such as virtual screening via property prediction. However, progress in polymer ML is hampered…

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 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…

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…

The rapid expansion of remote sensing image archives demands the development of strong and efficient techniques for content-based image retrieval (RS-CBIR). This paper presents REJEPA (Retrieval with Joint-Embedding Predictive…

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…

Accurately modeling and controlling vehicle exhaust emissions during transient events, such as rapid acceleration, is critical for meeting environmental regulations and optimizing powertrains. Conventional data-driven methods, such as…

In high energy physics, self-supervised learning (SSL) methods have the potential to aid in the creation of machine learning models without the need for labeled datasets for a variety of tasks, including those related to jets -- narrow…

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,…

This paper explores the automated process of determining stem compatibility by identifying audio recordings of single instruments that blend well with a given musical context. To tackle this challenge, we present Stem-JEPA, a novel…

Single-cell foundation models learn by reconstructing masked gene expression, implicitly treating technical noise as signal. With dropout rates exceeding 90%, reconstruction objectives encourage models to encode measurement artifacts rather…

Predicting satellite imagery requires a balance between structural accuracy and textural detail. Standard deterministic methods like PredRNN or SimVP minimize pixel-based errors but suffer from the "regression to the mean" problem,…

World models compress rich sensory streams into compact latent codes that anticipate future observations. We let separate agents acquire such models from distinct viewpoints of the same environment without any parameter sharing or…

Joint-Embedding Predictive Architectures (JEPAs), a powerful class of self-supervised models, exhibit an unexplained ability to cluster time-series data by their underlying dynamical regimes. We propose a novel theoretical explanation for…

Self-Supervised Learning (SSL) has shifted from pixel-level reconstruction to latent space prediction, spearheaded by the Joint Embedding Predictive Architecture (JEPA). While effective, standard JEPA models typically rely on a…