2025/06/01 by Muhammad Qasim Ali, Aditya Sridhar, Ali, Muhammad Qasim +8 · 1 voice · 3 citations
Computer Science · Engineering · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Robotic Locomotion and Control #Robotics (cs.RO) #cs.AI #cs.RO
paper · pdf · doi:10.48550/arxiv.2506.01182
openalex publication_date 2025/06/01 · arxiv published 2025/06/01 · arxiv updated 2025/07/08 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Humanoid robots, with their human-like form, are uniquely suited for interacting in environments built for people. However, enabling humanoids to reason, plan, and act in complex open-world settings remains a challenge. World models, models that predict the future outcome of a given action, can support these capabilities by serving as a dynamics model in long-horizon planning and generating synthetic data for policy learning. We introduce Humanoid World Models (HWM), a family of lightweight, open-source models that forecast future egocentric video conditioned on humanoid control tokens. We train two types of generative models, Masked Transformers and Flow-Matching, on 100 hours of humanoid demonstrations. Additionally, we explore architectural variants with different attention mechanisms and parameter-sharing strategies. Our parameter-sharing techniques reduce model size by 33-53% with minimal impact on performance or visual fidelity. HWMs are designed to be trained and deployed in practical academic and small-lab settings, such as 1-2 GPUs.