34 papers
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…
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…
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…
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…
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…
S-JEPA : Soft Clustering Anchors for Self-Supervised Speech Representation Learning
Georgios Ioannides, Adrian Kieback, Judah Goldfeder +5
Self-supervised speech encoders are predominantly trained by predicting discrete hard cluster IDs at masked positions, a recipe that collapses acoustic ambiguity at category bounda…