2 papers
cs.AI2026
WAM-OPD: On-Policy Distillation for World Action Models
Liuhaichen Yang, Zhuang Jiang, Chenchao Sheng +1
World action models (WAMs) couple visual future prediction with robot action generation, but accelerated students can lose task capabilities during distillation and later encounter…
cs.RO2026
Guided Action Flow: Q-Guided Inference for Flow-Matching Vision-Language-Action Policies
Liuhaichen Yang, Zhuang Jiang, Chenchao Sheng +1
Deploying a pretrained flow-matching vision-language-action (VLA) policy on a particular robot and workspace often calls for task-specific adaptation, while full- policy fine-tunin…