Showing cs.ROShow all
2 papers · 1 filter
cs.RO2026
Agent Priors-guided Policy Learning
Puming Jiang, Tianrun Hu, Haozhe Du +4
Robots that learn from a few demonstrations often require two forms of generalization. Compositional generalization recombines skills to solve new tasks, and skill generalization l…
cs.RO2026
Guided Streaming Stochastic Interpolant Policy
Puming Jiang, Meiyi Wang, Kelvin Lin +2
Inference-time guidance is essential for steering generative robot policies toward dynamic objectives without retraining, yet existing methods are largely confined to chunk-based a…