Haiweng Xu — accepted AI-conference papers

2026

Joint-Aligned Latent Action: Towards Scalable VLA Pretraining in the Wild

Hao Luo, Ye Wang, Wanpeng Zhang, Haoqi Yuan, Yicheng Feng, Haiweng Xu +2

CVPR 2026

Despite progress, Vision-Language-Action models (VLAs) are limited by a scarcity of large-scale, diverse robot data. While human manipulation videos offer a rich alternative, existing methods are forced to choose between small, precisely-labeled datasets and vast in-the-wild footage with unreliable

Cited by 0 Source ↗code ↗Scholar ↗

2026

Vision-Language-Action Pretraining from Large-Scale Human Videos

Hao Luo, Yicheng Feng, Wanpeng Zhang, Sipeng Zheng, Ye Wang, Haoqi Yuan +5

ICML 2026poster

Existing Vision-Language-Action (VLA) models struggle with complex manipulation tasks requiring high dexterity and generalization, primarily due to their reliance on synthetic data with significant sim-to-real gaps or limited teleoperated demonstrations. To address this bottleneck, we propose levera…

Cited by 0 Source ↗Scholar ↗