📌Abstract

Learning a general humanoid whole-body con- troller is challenging because practical reference motions can exhibit noise and inconsistencies after being transferred to the robot domain, and local defects may be amplified by closed- loop execution, causing drift or failure in highly dynamic and contact-rich behaviors. We propose a dynamics-conditioned command aggregation framework that uses a causal temporal encoder to summarize recent proprioception and a multi-head cross-attention command encoder to selectively aggregate a context window based on the current dynamics. We further integrate a fall recovery curriculum with random unstable initialization and an annealed upward assistance force to improve robustness and disturbance rejection. The resulting policy requires only about 3.5 hours of motion data and supports single-stage end-to-end training without distillation. The proposed method is evaluated under diverse reference inputs and challenging motion regimes, demonstrating zero- shot transfer to unseen motions as well as robust sim-to-real transfer on a physical humanoid robot.