Related papers: Rethinking JEPA: Compute-Efficient Video SSL with …

Self-supervised learning (SSL) is able to build latent representations that generalize well to unseen data. However, only a few SSL techniques exist for the online CL setting, where data arrives in small minibatches, the model must comply…

Masked video modeling, such as VideoMAE, is an effective paradigm for video self-supervised learning (SSL). However, they are primarily based on reconstructing pixel-level details on natural videos which have substantial temporal…

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…

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,…

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…

Aerodynamic surrogate models are increasingly used to replace repeated high-fidelity CFD evaluations in many-query design settings, but current approaches still face two important limitations: they often scale poorly to the very large…

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…

Generative models, from diffusion models to large language models, achieve remarkable performance but at a cost in training data orders of magnitude larger than what biological learners require. An alternative paradigm has emerged in which…

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…

Joint Embedding Predictive Architectures (JEPA) are a novel self supervised training technique that have shown recent promise across domains. We introduce BERT-JEPA (BEPA), a training paradigm that adds a JEPA training objective to…

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…

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…

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…

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,…

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…

Electroencephalography (EEG) is a widely used tool for studying brain function, with applications in clinical neuroscience, diagnosis, and brain-computer interfaces (BCIs). Recent EEG foundation models trained on large unlabeled corpora aim…

For video-text retrieval, the use of CLIP has been a de facto choice. Since CLIP provides only image and text encoders, this consensus has led to a biased paradigm that entirely ignores the sound track of videos. While several attempts have…

We present Video Pre-trained Transformer. VPT uses four SOTA encoder models from prior work to convert a video into a sequence of compact embeddings. Our backbone, based on a reference Flan-T5-11B architecture, learns a universal…

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…

We study semi-supervised learning (SSL) for vision transformers (ViT), an under-explored topic despite the wide adoption of the ViT architectures to different tasks. To tackle this problem, we propose a new SSL pipeline, consisting of first…