# MotionGlot: A Multi-Embodied Motion Generation Model

arXiv: https://arxiv.org/abs/2410.16623 · HTML: https://mlsanity.com/paper/2410.16623/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Oct 2024.

## Built on by (most cited first, 5 of 5)

- [The One RING: a Robotic Indoor Navigation Generalist](https://mlsanity.com/paper/2412.14401/) (2024)
- [Discrete Tokenization for Multimodal LLMs: A Comprehensive Survey](https://mlsanity.com/paper/2507.22920/) (2025)
- [λ: A Benchmark for Data-Efficiency in Long-Horizon Indoor Mobile Manipulation Robotics](https://mlsanity.com/paper/2412.05313/) (2024)
- [DreamControl-v2: Simpler and Scalable Autonomous Humanoid Skills via Trainable Guided Diffusion Priors](https://mlsanity.com/paper/2604.00202/) (2026)
- [Multi-Modal Controlled Coherent Motion Generation](https://mlsanity.com/paper/2609.11439/) (2026)

## Abstract (arXiv)

This paper introduces MotionGlot, a model that can generate motion across multiple embodiments with different action dimensions, such as quadruped robots and human bodies. By leveraging the well-established training procedures commonly used in large language models (LLMs), we introduce an instruction-tuning template specifically designed for motionrelated tasks. Our approach demonstrates that the principles underlying LLM training can be successfully adapted to learn a wide range of motion generation tasks across multiple embodiments with different action dimensions. We demonstrate the various abilities of MotionGlot on a set of 6 tasks and report an average improvement of 35.3% across tasks. Additionally, we contribute two new datasets: (1) a dataset of expert-controlled quadruped locomotion with approximately 48,000 trajectories paired with direction-based text annotations, and (2) a dataset of over 23,000 situational text prompts for human motion generation tasks. Finally, we conduct hardware experiments to validate the capabilities of our system in real-world applications.