5 papers
Memorize, Adapt, Ignore: Diagnosing Robot Learning Mechanisms under Training Data Variation
Ke Zhang, Danica J. Sutherland, Chao Liu
Training data variation, whether through designing a domain randomization (DR) scheme in simulation or curating demonstrations for imitation learning, is a primary lever for improv…
DiagGen: Agentic Generation of Deformable Assets with Sim-based Diagnostics for Robotic Simulation
Guanxiong Chen, Yiduo Qu, Qianjun Xia +12
While simulation-ready deformable assets are essential for in-silico robotic manipulation tasks, existing generation frameworks typically assess physical plausibility after generat…
WorldContact: A Contact-Centric World Model for Scalable Robot Learning
Caoliwen Wang, Mengdi Wang, Heng Zhang +7
Adapting robots to new objects and tasks requires interaction experience that can be costly to obtain. We present WorldContact, a contact-centric world model for deformable-object…
Agentic Real2Sim: Physics-based World Modeling with Vision-Language Agents
Guanxiong Chen, Qianjun Xia, Jiawei Peng +24
Real-to-sim conversion for robotic interaction with objects remains labor-intensive because it requires more than visual reconstruction: a streamlined real2sim process must recover…
Learning social norms enhances compatibility in dynamic human-AI coordination
Yi Yang, Siyuan Liu, Xin Gao +4
Humans continuously coordinate with others in dynamic interactions, often through implicit, hard-to-quantify social norms that act as shared tacit expectations among interacting ag…