Hugging Face Trending Papers

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

Read the original on Hugging Face Trending Papers →

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.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

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
arXiv Machine Learning
Jun 5

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

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.

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