activity
20242026
collaborators

7 papers

cs.RO2026

PointWorld: Scaling 3D World Models for In-The-Wild Robotic Manipulation

Wenlong Huang, Yu-Wei Chao, Arsalan Mousavian +4

Humans anticipate, from a glance and a contemplated action of their bodies, how the 3D world will respond, a capability that is equally vital for robotic manipulation. We introduce…

cs.RO2025

VT-Refine: Learning Bimanual Assembly with Visuo-Tactile Feedback via Simulation Fine-Tuning

Binghao Huang, Jie Xu, Iretiayo Akinola +8

Humans excel at bimanual assembly tasks by adapting to rich tactile feedback -- a capability that remains difficult to replicate in robots through behavioral cloning alone, due to…

cs.RO2025

Dexplore: Scalable Neural Control for Dexterous Manipulation from Reference-Scoped Exploration

Sirui Xu, Yu-Wei Chao, Liuyu Bian +4

Hand-object motion-capture (MoCap) repositories offer large-scale, contact-rich demonstrations and hold promise for scaling dexterous robotic manipulation. Yet demonstration inaccu…

cs.RO2025

3D FlowMatch Actor: Unified 3D Policy for Single- and Dual-Arm Manipulation

Nikolaos Gkanatsios, Jiahe Xu, Matthew Bronars +3

We present 3D FlowMatch Actor (3DFA), a 3D policy architecture for robot manipulation that combines flow matching for trajectory prediction with 3D pretrained visual scene represen…

cs.CV2025

Cosmos World Foundation Model Platform for Physical AI

NVIDIA, :, Niket Agarwal +76

Physical AI needs to be trained digitally first. It needs a digital twin of itself, the policy model, and a digital twin of the world, the world model. In this paper, we present th…

cs.RO2025

Slot-Level Robotic Placement via Visual Imitation from Single Human Video

Dandan Shan, Kaichun Mo, Wei Yang +4

The majority of modern robot learning methods focus on learning a set of pre-defined tasks with limited or no generalization to new tasks. Extending the robot skillset to novel tas…