arXiv Machine Learning By Lucas Maes, Quentin Le Lidec, Damien Scieur, Yann LeCun, Randall Balestriero

LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels

Read the original on arXiv Machine Learning →

arXiv:2603. 19312v3 Announce Type: replace Abstract: Joint Embedding Predictive Architectures (JEPAs) offer a compelling framework for learning world models in compact latent spaces, yet existing methods remain fragile, relying on complex multi-term losses, exponential moving averages, pre-trained encoders, or auxiliary supervision to avoid representation collapse.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning
Jun 26

Fast LeWorldModel

arXiv:2606. 26217v1 Announce Type: new Abstract: Joint-Embedding Predictive Architectures (JEPAs), including recent LeWorldModel (LeWM), have become a promising foundation for reconstruction-free visual world models.

By Yuntian Gao, Xiangyu Xu
arXiv Machine Learning
Jul 30

Temporally Centered SIGReg Improves Multi-Task LeWorldModel Learning: From Analysis to Method

arXiv:2607. 26924v1 Announce Type: new Abstract: Recent work on LeWorldModel (LeWM) has shown that the Sketched Isotropic Gaussian Regularizer (SIGReg) enables stable end-to-end world-model learning from pixels by regularizing the latent marginal distribution toward an isotropic Gaussian, thereby preventing representation collapse.

By Chang Liu, Fei Suo, Yanzhou Jin, Yusuke Iwasawa, Yutaka Matsuo, Yaonan Zhu
Hugging Face Trending Papers
Jul 29

Temporally Centered SIGReg Improves Multi-Task LeWorldModel Learning: From Analysis to Method

Recent work on LeWorldModel (LeWM) has shown that the Sketched Isotropic Gaussian Regularizer (SIGReg) enables stable end-to-end world-model learning from pixels by regularizing the latent marginal distribution toward an isotropic Gaussian, thereby preventing representation collapse. While effective and elegant in single-task settings, this recipe does not extend reliably to multi-task training, leading to substantially worse downstream behavior-cloning performance.