Showing cs.ROShow all
2 papers · 1 filter
cs.RO2026
Awomo-SimDataEngine: Agentic Simulation-ReadyWorld Generation
PhysicalRSI Team, Danjiao Ma, Enhui Ma +21
Generating useful robot-training data requires more than visually plausiblescenes: objects must support interaction, placements must remain physicallyvalid, and tasks must admit re…
cs.RO2026
An Action Is Worth One Patch: Unified World-Action Modeling with PatchWAM
Tianheng Wang, Zhou Xie, Heng Jia +3
Generative visual models offer a foundation for learning representations of physical dynamics, yet their extension to continuous control raises a fundamental question: do visual pr…