Quo Vadis, Motion Generation? From Large Language Models to Large Motion Models

Ye Wang, Sipeng Zheng, Bin Cao, Qianshan Wei, Qin Jin, Zongqing Lu

Keywords: human motion generation, large motion model, large language model

Abstract:

Inspired by the recent success of LLMs, the field of human motion understanding has increasingly shifted towards the development of large motion models.
Despite some progress, current state-of-the-art works remain far from achieving truly generalist models, largely due to the lack of large-scale, high-quality motion data.
To address this, we present MotionBase, the first million-level motion benchmark, offering 15 times the data volume of the previous largest dataset and featuring multimodal data with hierarchically detailed descriptions.
By leveraging this vast dataset, our large motion model demonstrates strong performance across a broad range of motions, including unseen ones.
Through systematic investigation, we underscore the importance of scaling both data and model size, with synthetic data and pseudo labels playing a crucial role in mitigating data acquisition costs.
Moreover, our research reveals the limitations of existing evaluation metrics, particularly in handling out-of-domain text instructions --- an issue that has long been overlooked.
In addition to these, we introduce a novel 2D lookup-free tokenizer for motion quantization, which preserves motion information and expands codebook capacity, further enhancing the representative ability of large motion models.
The release of MotionBase and the insights gained from this study are expected to pave the way for the development of more powerful and versatile motion generation models.
Our code and database will be released at \url{https://anonymous.4open.science/r/MotionBase}.

Primary Area: generative models

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 4241