الباحثون

Xiaogang Wang

المنشورات 2

نسخة أولية وصول مفتوح

OmniDex: Scaling Dexterous Hand Grasping to Diverse Cluttered Scenes

Naiyu Fang, Zhongjin Luo, Yuxin Mo وآخرون · 2026

Dexterous grasping is the foundational primitive in embodied AI, demanding massive data to train robust models. As real-world data collection is expensive, simulation has become the mainstream paradigm. Yet, while cluttered scenes best reflect real-world applications, learning to grasp within them is bottlenecked by a …

نسخة أولية وصول مفتوح

Rewiring Semantics, Dynamics, and Control: A Simple yet Effective Action-Centric Tri-Stream Transformer

Shuang Luo, Yilun Kong, Yunpeng Qing وآخرون · 2026

Vision-Language-Action (VLA) models have emerged as a prominent framework for complex robotic manipulation, building on the strong semantic understanding of pretrained Vision-Language Models (VLMs). However, such VLM backbones offer insufficient physical dynamics priors, which limits the generalization capabilities of …

المؤلفون المشاركون