الباحثون

Zhenshan Bing

المنشورات 2

نسخة أولية وصول مفتوح

LiteNWM: Efficient Latent World Models for Onboard Visual Navigation in the Wild

Linkai Liu, Yuntian Zhang, Zhenshan Bing وآخرون · 2026

Direct visual navigation policies generate trajectories efficiently but do not explicitly evaluate their future consequences. Generative navigation world models provide this foresight through visual rollouts, which are costly when evaluating multiple candidates. We present LiteNWM, a latent navigation world model that …

نسخة أولية وصول مفتوح

VidAct: Learning Manipulation from In-the-Wild Videos with Object-Centric 3D Awareness

Hang Li, Mingxin Zhang, Zihan Wu وآخرون · 2026

Video demonstrations offer a scalable alternative to costly robot data for learning manipulation, yet existing reconstruction-based approaches often rely on constrained camera viewpoints or human-to-robot retargeting, while the reconstructed trajectories are difficult to adapt to new objects configurations without dist …

المؤلفون المشاركون