English
Related papers

Related papers: VL-JEPA: Joint Embedding Predictive Architecture f…

200 papers

Recently, self-supervised representation learning relying on vast amounts of unlabeled data has been explored as a pre-training method for autonomous driving. However, directly applying popular contrastive or generative methods to this…

Robotics · Computer Science 2025-10-08 Haoran Zhu , Zhenyuan Dong , Kristi Topollai , Beiyao Sha , Anna Choromanska

In this work, we introduce Mask-JEPA, a self-supervised learning framework tailored for mask classification architectures (MCA), to overcome the traditional constraints associated with training segmentation models. Mask-JEPA combines a…

Computer Vision and Pattern Recognition · Computer Science 2024-07-16 Dong-Hee Kim , Sungduk Cho , Hyeonwoo Cho , Chanmin Park , Jinyoung Kim , Won Hwa Kim

Video representation learning is an increasingly important topic in machine learning research. We present Video JEPA with Variance-Covariance Regularization (VJ-VCR): a joint-embedding predictive architecture for self-supervised video…

Computer Vision and Pattern Recognition · Computer Science 2024-12-17 Katrina Drozdov , Ravid Shwartz-Ziv , Yann LeCun

Vision-Language Models (VLMs) leverage aligned visual encoders to transform images into visual tokens, allowing them to be processed similarly to text by the backbone large language model (LLM). This unified input paradigm enables VLMs to…

Computer Vision and Pattern Recognition · Computer Science 2025-03-18 Bangzheng Li , Fei Wang , Wenxuan Zhou , Nan Xu , Ben Zhou , Sheng Zhang , Hoifung Poon , Muhao Chen

End-to-end autonomous driving increasingly leverages self-supervised video pretraining to learn transferable planning representations. However, pretraining video world models for scene understanding has so far brought only limited…

Computer Vision and Pattern Recognition · Computer Science 2026-01-30 Linhan Wang , Zichong Yang , Chen Bai , Guoxiang Zhang , Xiaotong Liu , Xiaoyin Zheng , Xiao-Xiao Long , Chang-Tien Lu , Cheng Lu

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

We present EB-JEPA, an open-source library for learning representations and world models using Joint-Embedding Predictive Architectures (JEPAs). JEPAs learn to predict in representation space rather than pixel space, avoiding the pitfalls…

Computer Vision and Pattern Recognition · Computer Science 2026-04-09 Basile Terver , Randall Balestriero , Megi Dervishi , David Fan , Quentin Garrido , Tushar Nagarajan , Koustuv Sinha , Wancong Zhang , Mike Rabbat , Yann LeCun , Amir Bar

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

Video Joint Embedding Predictive Architectures (V-JEPA) learn generalizable off-the-shelf video representation by predicting masked regions in latent space with an exponential moving average (EMA)-updated teacher. While EMA prevents…

Machine Learning · Computer Science 2025-09-30 Xianhang Li , Chen Huang , Chun-Liang Li , Eran Malach , Josh Susskind , Vimal Thilak , Etai Littwin

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…

Computer Vision and Pattern Recognition · Computer Science 2025-12-24 Sihan Xu , Ziqiao Ma , Wenhao Chai , Xuweiyi Chen , Weiyang Jin , Joyce Chai , Saining Xie , Stella X. Yu

World models for partially observed environments must imagine multiple compatible hidden futures and steer between them under counterfactual actions. Joint Embedding Predictive Architectures (JEPAs) do this in latent space, but a…

Machine Learning · Computer Science 2026-05-26 Santosh Kumar Radha , Oktay Goktas

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…

Machine Learning · Computer Science 2022-11-22 Vlad Sobal , Jyothir S , Siddhartha Jalagam , Nicolas Carion , Kyunghyun Cho , Yann LeCun

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…

Computer Vision and Pattern Recognition · Computer Science 2024-04-15 Adrien Bardes , Quentin Garrido , Jean Ponce , Xinlei Chen , Michael Rabbat , Yann LeCun , Mahmoud Assran , Nicolas Ballas

Image and language modeling is of crucial importance for vision-language pre-training (VLP), which aims to learn multi-modal representations from large-scale paired image-text data. However, we observe that most existing VLP methods focus…

Computer Vision and Pattern Recognition · Computer Science 2022-08-22 Sunan He , Taian Guo , Tao Dai , Ruizhi Qiao , Chen Wu , Xiujun Shu , Bo Ren

Currently, inspired by the success of vision-language models (VLMs), an increasing number of researchers are focusing on improving VLMs and have achieved promising results. However, most existing methods concentrate on optimizing the…

Computer Vision and Pattern Recognition · Computer Science 2024-09-23 Dawei Yan , Pengcheng Li , Yang Li , Hao Chen , Qingguo Chen , Weihua Luo , Wei Dong , Qingsen Yan , Haokui Zhang , Chunhua Shen

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

While MLLMs perform well on perceptual tasks, they lack precise multimodal alignment, limiting performance. To address this challenge, we propose Vision Dynamic Embedding-Guided Pretraining (VDEP), a hybrid autoregressive training paradigm…

Computer Vision and Pattern Recognition · Computer Science 2025-02-14 Mingxiao Li , Fang Qu , Zhanpeng Chen , Na Su , Zhizhou Zhong , Ziyang Chen , Nan Du , Xiaolong Li

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…

Information Retrieval · Computer Science 2025-08-08 Minh-Anh Nguyen , Dung D. Le

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,…

Computer Vision and Pattern Recognition · Computer Science 2023-07-25 Adrien Bardes , Jean Ponce , Yann LeCun

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…

Machine Learning · Computer Science 2025-01-22 Geri Skenderi , Hang Li , Jiliang Tang , Marco Cristani