HumanX is a new framework compiling monocular human video into generalizable interaction skills for humanoid robots, combining an anchor-centric data pipeline with an interaction-prioritized learning…

#HumanX #humanoidRobots #robotLearning #imitationLearning
https://arxiv.org/abs/2602.02473

arXiv paper proposes a closed-loop framework that iteratively refines imitation-learning policies via LLM analysis of rollout data, reporting up to 15% gains on car racing and door opening.

#ImitationLearning #LLMAgents #PolicyRefinement #Robotics
https://arxiv.org/abs/2610.01652