{"ID":2835396,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.22963","arxiv_id":"2511.22963","title":"Commanding Humanoid by Free-form Language: A Large Language Action Model with Unified Motion Vocabulary","abstract":"Enabling humanoid robots to follow free-form natural language commands is a critical step toward seamless human-robot interaction and general-purpose embodied AI. However, existing methods remain limited, often constrained to simple instructions or forced to sacrifice motion diversity for physical plausibility. To address this gap, we present Humanoid-LLA, a Large Language Action model that translates unconstrained natural language directly into executable whole-body motions for humanoid robots. Our approach tackles two core challenges: paired language-humanoid motion data scarcity and physical instability. First, we bridge high-level language semantics with physically-grounded control by learning a unified human-humanoid motion vocabulary. Second, we introduce a novel two-stage fine-tuning framework that begins with supervised motion Chain-of-Thought learning, followed by reinforcement learning refined with physical feedback to ensure robustness and stability. Extensive evaluation in simulation and real-world cross-embodiment experiments demonstrates that Humanoid-LLA achieves superior generalization to novel language commands and diverse motion generation while maintaining high physical fidelity.","short_abstract":"Enabling humanoid robots to follow free-form natural language commands is a critical step toward seamless human-robot interaction and general-purpose embodied AI. However, existing methods remain limited, often constrained to simple instructions or forced to sacrifice motion diversity for physical plausibility. To addr...","url_abs":"https://arxiv.org/abs/2511.22963","url_pdf":"https://arxiv.org/pdf/2511.22963v3","authors":"[\"Zhirui Liu\",\"Kaiyang Ji\",\"Ke Yang\",\"Yahao Fan\",\"Jingyi Yu\",\"Ye Shi\",\"Jingya Wang\"]","published":"2025-11-28T08:11:24Z","proceeding":"cs.RO","tasks":"[\"cs.RO\",\"cs.AI\"]","methods":"[\"Reinforcement Learning\"]","has_code":false}