most citedCausal-JEPA: Learning World Models through Object-Level Latent Masking

5 citations · 6 across the 18 of their papers we have counts for

collaborators

35 papers

cs.LG2026

LpWM: A Case for Sparse Representations in World Models

Yilun Kuang, Yash Dagade, Quentin Le Lidec +3

Joint-embedding predictive architectures (JEPAs) learn latent dynamics for planning and avoid representation collapse by matching features to maximum-entropy distributions such as…

cs.CV2026

Self-supervised DXA representations encode multi-system disease risk, biological aging and heritability

Gil Sasson, Zachary Levine, Smadar Shilo +9

Whole-body dual-energy X-ray absorptiometry (DXA) scans are routinely acquired to measure bone density and regional body composition, leaving their spatial structure largely unused…

cs.SD2026

Music-JEPA: Learning a World Model of Sound from Action

Ziyu Wang, Kun Fang, Yann LeCun

Joint Embedding Predictive Architectures (JEPA) have recently emerged as a paradigm for learning world models by predicting latent representations, offering a promising direction f…

cs.RO2026

Patch Policy: Efficient Embodied Control via Dense Visual Representations

Gaoyue Zhou, Zichen Jeff Cui, Ada Langford +3

Pretrained dense visual features from Vision Transformers (ViTs) are powerful yet have been underutilized in robot learning. Modern robot policies either compress each observation…

cs.LG2026

AdaJEPA: An Adaptive Latent World Model

Ying Wang, Oumayma Bounou, Yann LeCun +1

Latent world models enable planning from high-dimensional observations by predicting future states in a compact latent space. However, these models are typically kept frozen at tes…

cs.RO2026

SkyJEPA: Learning Long-Horizon World Models for Zero-Shot Sim-to-Real Control of Quadrotors

Pratyaksh Rao, Wancong Zhang, Randall Balestriero +2

Accurate dynamics models are critical for informed decision-making in robotic systems, particularly for agile aerial vehicles operating under uncertainty. Neural network dynamics m…