{"ID":2877678,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.19926","arxiv_id":"2508.19926","title":"FARM: Frame-Accelerated Augmentation and Residual Mixture-of-Experts for Physics-Based High-Dynamic Humanoid Control","abstract":"Unified physics-based humanoid controllers are pivotal for robotics and character animation, yet models that excel on gentle, everyday motions still stumble on explosive actions, hampering real-world deployment. We bridge this gap with FARM (Frame-Accelerated Augmentation and Residual Mixture-of-Experts), an end-to-end framework composed of frame-accelerated augmentation, a robust base controller, and a residual mixture-of-experts (MoE). Frame-accelerated augmentation exposes the model to high-velocity pose changes by widening inter-frame gaps. The base controller reliably tracks everyday low-dynamic motions, while the residual MoE adaptively allocates additional network capacity to handle challenging high-dynamic actions, significantly enhancing tracking accuracy. In the absence of a public benchmark, we curate the High-Dynamic Humanoid Motion (HDHM) dataset, comprising 3593 physically plausible clips. On HDHM, FARM reduces the tracking failure rate by 42.8\\% and lowers global mean per-joint position error by 14.6\\% relative to the baseline, while preserving near-perfect accuracy on low-dynamic motions. These results establish FARM as a new baseline for high-dynamic humanoid control and introduce the first open benchmark dedicated to this challenge. The code and dataset will be released at https://github.com/Colin-Jing/FARM.","short_abstract":"Unified physics-based humanoid controllers are pivotal for robotics and character animation, yet models that excel on gentle, everyday motions still stumble on explosive actions, hampering real-world deployment. We bridge this gap with FARM (Frame-Accelerated Augmentation and Residual Mixture-of-Experts), an end-to-end...","url_abs":"https://arxiv.org/abs/2508.19926","url_pdf":"https://arxiv.org/pdf/2508.19926v1","authors":"[\"Tan Jing\",\"Shiting Chen\",\"Yangfan Li\",\"Weisheng Xu\",\"Renjing Xu\"]","published":"2025-08-27T14:35:37Z","proceeding":"cs.RO","tasks":"[\"cs.RO\"]","methods":"[]","has_code":false,"code_links":[{"ID":610408,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2877678,"paper_url":"https://arxiv.org/abs/2508.19926","paper_title":"FARM: Frame-Accelerated Augmentation and Residual Mixture-of-Experts for Physics-Based High-Dynamic Humanoid Control","repo_url":"https://github.com/Colin-Jing/FARM","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}