Related papers: Sub-JEPA: Subspace Gaussian Regularization for Sta…

A long-standing challenge in AI is to develop agents capable of solving a wide range of physical tasks and generalizing to new, unseen tasks and environments. A popular recent approach involves training a world model from state-action…

We evaluate JEPA-style predictive representation learning versus reconstruction-based autoencoders on a controlled "TV-series" linear dynamical system with known latent state and a single noise parameter. While an initial comparison…

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…

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…

Epistemic Planning (EP) is an important research area dedicated to reasoning about the knowledge and beliefs of agents in multi-agent cooperative or adversarial settings. The Justified Perspective (JP) model is the state-of-the-art approach…

Variational Autoencoders (VAEs) have experienced recent success as data-generating models by using simple architectures that do not require significant fine-tuning of hyperparameters. However, VAEs are known to suffer from…

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…

A fundamental open question in self-supervised learning (SSL) is the explicit characterization of the optimal geometry of the learned representations. Recently, LeJEPA identified isotropic Gaussian embeddings as optimal for minimizing…

Self-supervised representation learning often relies on deterministic predictive architectures to align context and target views in latent space. While effective in many settings, such methods are limited in genuinely multi-modal inverse…

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…

We introduce a self-supervised framework for learning predictive and structured representations of wireless channels by modeling the temporal evolution of channel state information (CSI) in a compact latent space. Our method casts the…

Joint-Embedding Predictive Architectures (JEPAs) aim to learn representations by predicting target embeddings from context embeddings, inducing a scalar compatibility energy in a latent space. In contrast, Quasimetric Reinforcement Learning…

We introduce VL-JEPA, a vision-language model built on a Joint Embedding Predictive Architecture (JEPA). Instead of autoregressively generating tokens as in classical VLMs, VL-JEPA predicts continuous embeddings of the target texts. By…

Geospatial foundation models compress multispectral observations into dense embeddings increasingly used in natural-language environmental reasoning systems. A single planetary-scale model, e.g. Google AlphaEarth, handles broad…

Recent breakthroughs in self-supervised Joint-Embedding Predictive Architectures (JEPAs) have established that regularizing Euclidean representations toward isotropic Gaussian priors yields provable gains in training stability and…

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…

Representation alignment (REPA) guides generative training by distilling representations from a strong, pretrained vision encoder to intermediate diffusion features. We investigate a fundamental question: what aspect of the target…

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…

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…

We introduce a two-stage self-supervised framework that combines the Joint-Embedding Predictive Architecture (JEPA) with a Density Adaptive Attention Mechanism (DAAM) for learning robust speech representations. Stage~1 uses JEPA with DAAM…