English
Related papers

Related papers: Stem-JEPA: A Joint-Embedding Predictive Architectu…

200 papers

The Joint-Embedding Predictive Architecture (JEPA) is often seen as a non-generative alternative to likelihood-based self-supervised learning, emphasizing prediction in representation space rather than reconstruction in observation space.…

Machine Learning · Computer Science 2026-03-23 Moritz Gögl , Christopher Yau

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…

Machine Learning · Computer Science 2024-07-08 Etai Littwin , Omid Saremi , Madhu Advani , Vimal Thilak , Preetum Nakkiran , Chen Huang , Joshua Susskind

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…

Machine Learning · Computer Science 2025-11-17 Randall Balestriero , Yann LeCun

A flexible recommendation and retrieval system requires music similarity in terms of multiple partial elements of musical pieces to allow users to select the element they want to focus on. A method for music similarity learning using…

Sound · Computer Science 2025-07-18 Yuka Hashizume , Li Li , Atsushi Miyashita , Tomoki Toda

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…

Machine Learning · Computer Science 2026-03-19 Aleksandar Vujinovic , Aleksandar Kovacevic

The development of multimodal models for pulmonary nodule diagnosis is limited by the scarcity of labeled data and the tendency for these models to overfit on the training distribution. In this work, we leverage self-supervised learning…

Computer Vision and Pattern Recognition · Computer Science 2025-09-22 Thomas Z. Li , Aravind R. Krishnan , Lianrui Zuo , John M. Still , Kim L. Sandler , Fabien Maldonado , Thomas A. Lasko , Bennett A. Landman

Music classification has been one of the most popular tasks in the field of music information retrieval. With the development of deep learning models, the last decade has seen impressive improvements in a wide range of classification tasks.…

Sound · Computer Science 2023-07-03 Yiwei Ding , Alexander Lerch

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…

Computer Vision and Pattern Recognition · Computer Science 2024-05-29 Shentong Mo , Sukmin Yun

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…

High Energy Physics - Phenomenology · Physics 2024-12-13 Subash Katel , Haoyang Li , Zihan Zhao , Raghav Kansal , Farouk Mokhtar , Javier Duarte

Self-supervised learning has emerged as a powerful paradigm for learning visual representations without manual annotations, yet most methods still operate on a single modality and therefore miss the complementary structure available from…

Computer Vision and Pattern Recognition · Computer Science 2026-04-02 Ciem Cornelissen , Sam Leroux , Pieter Simoens

Genomic Foundation Models (GFMs) typically rely on Masked Language Modeling (MLM) or Next-Token Prediction (NTP) to learn the "Laws of Nature". While effective at capturing local syntax, these generative paradigms prioritize token-level…

We present Clin-JEPA, a multi-phase co-training framework for joint-embedding predictive (JEPA) pretraining on EHR patient trajectories. JEPA architectures have enabled latent-space planning in robotics and high-quality representation…

In wireless networked control systems, ensuring timely and reliable state updates from distributed devices to remote controllers is essential for robust control performance. However, when multiple devices transmit high-dimensional states…

Systems and Control · Electrical Eng. & Systems 2026-02-10 Abanoub M. Girgis , Ibtissam Labriji , Mehdi Bennis

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…

Machine Learning · Computer Science 2025-05-06 Jungwon Choi , Hyungi Lee , Byung-Hoon Kim , Juho Lee

Depression detection research has increased over the last few decades, one major bottleneck of which is the limited data availability and representation learning. Recently, self-supervised learning has seen success in pretraining text…

Human-Computer Interaction · Computer Science 2021-10-29 Pingyue Zhang , Mengyue Wu , Heinrich Dinkel , Kai Yu

Robotic imitation learning is often treated as reproducing demonstrated actions, but actions are inherently embodiment-specific. When demonstrations come from humans or robots with different morphology, kinematics, or action spaces, this…

Robotics · Computer Science 2026-05-21 Jingyang He , Guangrun Li , Jieyu Zhang , Chengkai Hou , Zhengping Che , Shanghang Zhang

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…

Computer Vision and Pattern Recognition · Computer Science 2024-09-25 Naiwen Hu , Haozhe Cheng , Yifan Xie , Shiqi Li , Jihua Zhu

Music mixing involves combining individual tracks into a cohesive mixture, a task characterized by subjectivity where multiple valid solutions exist for the same input. Existing automatic mixing systems treat this task as a deterministic…

Audio and Speech Processing · Electrical Eng. & Systems 2025-11-12 Eloi Moliner , Marco A. Martínez-Ramírez , Junghyun Koo , Wei-Hsiang Liao , Kin Wai Cheuk , Joan Serrà , Vesa Välimäki , Yuki Mitsufuji

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…

Computer Vision and Pattern Recognition · Computer Science 2025-10-02 Siheng Wan , Zhengtao Yao , Zhengdao Li , Junhao Dong , Yanshu Li , Yikai Li , Linshan Li , Haoyan Xu , Yijiang Li , Zhikang Dong , Huacan Wang , Jifeng Shen

This paper presents a three-tier modality alignment approach to learning text-image joint embedding, coined as JEMA, for cross-modal retrieval of cooking recipes and food images. The first tier improves recipe text embedding by optimizing…

Computer Vision and Pattern Recognition · Computer Science 2021-08-19 Zhongwei Xie , Ling Liu , Lin Li , Luo Zhong