WAM-Policy brings language-conditioned control to quadrupedal robots
The authors of an arXiv paper present WAM-Policy, a two-stage method that adapts a world action model pretrained for robot arms to language-conditioned locomotion and manipulation on arm-free quadrupeds. Their method combines cross-morphology adaptation, on-policy self-distillation, reinforcement learning and multi-teacher distillation; on the authors' QLM-Bench, an OPSD student retained a 76.7% score while sampling 14 times faster, and later training raised it to 85.0%. The authors also report deploying the OPSD student on a real Unitree Go2 Air, although these results currently come solely from their paper and abstract.
WAM-Policy presents a concrete route for applying language-conditioned world action models to arm-free quadrupedal loco-manipulation while sharply reducing sampling steps, a combination supported by the authors' simulated benchmark and physical-robot deployment.
Computer Science > Robotics
arXiv:2611.24011 (cs)
[Submitted on 18 Nov 2026]
Title:WAM-Policy: World Action Models with On-Policy Distillation for Quadrupedal Loco-Manipulation
Authors:Junlin Long, Xu Deng, Yiran Wang, Yue Yang, Yang Zhao, Zeyu Zhang
View a PDF of the paper titled WAM-Policy: World Action Models with On-Policy Distillation for Quadrupedal Loco-Manipulation, by Junlin Long and 5 other authors
#WAM-Policy#QLM-Bench#Unitree Go2 Air#On-Policy Self-Distillation#Multi-Teacher On-Policy Distillation