Related papers: Label-Efficient Grasp Joint Prediction with Point-…

World models require robust relational understanding to support prediction, reasoning, and control. While object-centric representations provide a useful abstraction, they are not sufficient to capture interaction-dependent dynamics. We…

In the field of 3D scene understanding, 3D scene graphs have emerged as a new scene representation that combines geometric and semantic information about objects and their relationships. However, learning semantic 3D scene graphs in a fully…

Joint Embedding Predictive Architectures (JEPA) have emerged as a powerful framework for learning general-purpose representations. However, these models often lack interpretability and suffer from inefficiencies due to dense embedding…

Protein language models are trained primarily with masked language modeling (MLM), which predicts amino-acid identities at masked positions. We ask whether latent-space prediction can complement these token-level objectives under matched…

Image-based Joint-Embedding Predictive Architecture (I-JEPA) offers a promising approach to visual self-supervised learning through masked feature prediction. However with the inherent visual uncertainty at masked positions, feature…

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…

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…

Pretraining on large labeled datasets is a prerequisite to achieve good performance in many computer vision tasks like 2D object recognition, video classification etc. However, pretraining is not widely used for 3D recognition tasks where…

Channel state information (CSI) provides a widely available sensing modality for human and environment perception, but existing CSI sensing models usually rely on task-specific supervised training and require substantial labeled data for…

Building on the Joint-Embedding Predictive Architecture (JEPA) paradigm, a recent self-supervised learning framework that predicts latent representations of masked regions in high-level feature spaces, we propose Audio-JEPA (Audio…

Latent prediction--where agents learn by predicting their own latents--has emerged as a powerful paradigm for training general representations in machine learning. In reinforcement learning (RL), this approach has been explored to define…

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…

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…

To realize a robust robotic grasping system for unknown objects in an unstructured environment, large amounts of grasp data and 3D model data for the object are required, the sizes of which directly affect the rate of successful grasps. To…

This paper presents RPEP, the first pre-training method for event-based 3D hand pose estimation using labeled RGB images and unpaired, unlabeled event data. Event data offer significant benefits such as high temporal resolution and low…

Grasping objects with limited or no prior knowledge about them is a highly relevant skill in assistive robotics. Still, in this general setting, it has remained an open problem, especially when it comes to only partial observability and…

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…

In this paper, we introduce a Grasp Manifold Estimator (GraspME) to detect grasp affordances for objects directly in 2D camera images. To perform manipulation tasks autonomously it is crucial for robots to have such graspability models of…

Self-supervised learning (SSL) has become an important approach in pretraining large neural networks, enabling unprecedented scaling of model and dataset sizes. While recent advances like I-JEPA have shown promising results for Vision…

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…