Hugging Face Trending Papers

LAWM-3D: Learning 3D-Aware Latent Actions from Human Videos for Generalizable Robot World Models

Read the original on Hugging Face Trending Papers →

World models enable agents to perform forward rollout and planning without real-world interaction. However, their application in open-world embodied intelligence remains limited by the high cost of action annotations and the heterogeneity of action spaces across platforms.

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

arXiv AI
Jun 2

From Human Videos to Robot Manipulation: A Survey on Scalable Vision-Language-Action Learning with Human-Centric Data

arXiv:2606. 00054v1 Announce Type: cross Abstract: Recent progress in generalizable embodied control has been driven by large-scale pretraining of Vision-Language-Action (VLA) models.

By Zhiyuan Feng, Qixiu Li, Huizhi Liang, Rushuai Yang, Yichao Shen, Zhiying Du, Zhaowei Zhang, Yu Deng, Li Zhao, Hao Zhao, Zongqing Lu, Oier Mees, Marc Pollefeys, Jiaolong Yang, Baining Guo
arXiv Machine Learning
Jun 15

$\mu_0$: A Scalable 3D Interaction-Trace World Model

arXiv:2606. 13769v1 Announce Type: cross Abstract: World models that capture how actions induce physical change enable scalable robot learning without reliance on embodiment-specific action labels.

By Seungjae Lee, Yoonkyo Jung, Jusuk Lee, Jonghun Shin, Amir Hossein Shahidzadeh, Yao-Chih Lee, H. Jin Kim, Jia-Bin Huang, Furong Huang