2 papers
cs.RO2026
Shared Execution-Clock Drifting Policy for Dynamic Precision Manipulation
Zhenchen Dong, Qingran Wu, Jinna Fu +4
Manipulation under time constraints requires both accurate actions and an execution rhythm that matches the evolving scene. This becomes critical when a robot must intercept moving…
cs.RO2026
HybridFlow: A 2-NFE Generative Policy for Real-Time Robotic Manipulation
Zhenchen Dong, Jinna Fu, Jiaming Wu +5
Generative policies for robotic manipulation must balance action accuracy with inference latency. We present HybridFlow, a three-stage policy inference procedure requiring two netw…