# Commanding Humanoid by Free-form Language: A Large Language Action Model with Unified Motion Vocabulary

arXiv: https://arxiv.org/abs/2511.22963 · HTML: https://mlsanity.com/paper/2511.22963/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Nov 2025.

## Built on by (most cited first, 7 of 7)

- [FRoM-W1: Towards General Humanoid Whole-Body Control with Language Instructions](https://mlsanity.com/paper/2601.12799/) (2026)
- [UniHM: Unified Dexterous Hand Manipulation with Vision Language Model](https://mlsanity.com/paper/2603.00732/) (2026)
- [PhyGile: Physics-Prefix Guided Motion Generation for Agile General Humanoid Motion Tracking](https://mlsanity.com/paper/2603.19305/) (2026)
- [DiscoForcing: A Unified Framework for Real-Time Audio-Driven Character Control with Diffusion Forcing](https://mlsanity.com/paper/2605.28491/) (2026)
- [From Scene-Centric to Observer-Centric: Modeling Observer-Aware Relations for 3D Scene Graph Generation](https://mlsanity.com/paper/2606.27412/) (2026)
- [What Language Does and What the Evidence Supports: A Functional Role Taxonomy and Evidence Audit of Language Grounding in Embodied Agents](https://mlsanity.com/paper/2608.03099/) (2026)
- [Sample, Simulate, Select: Physics-in-the-Loop Text-to-Motion for Humanoids Without Training](https://mlsanity.com/paper/2609.26420/) (2026)

## Abstract (arXiv)

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.