Journal article · 2026 · Open access

MotionRFT: Unified Reinforcement Fine-Tuning for Text-to-Motion Generation

Xiaofeng Tan, Wanjiang Weng, Hongsong Wang, Fang Zhao, Xin Geng, Liang Wang

IEEE Transactions on Pattern Analysis and Machine Intelligence, PP, 1–15 · Published 1 January 2026 · DOI 10.1109/tpami.2026.3741371

Open PDFView at the publisherCite this paper

In brief

“MotionRFT: Unified Reinforcement Fine-Tuning for Text-to-Motion Generation” is a 2026 journal article by Xiaofeng Tan and 5 co-authors, published in IEEE Transactions on Pattern Analysis and Machine Intelligence. OpenAlex counts 0 citations as of 16 November 2026. It is open access under a public domain licence: the full text is free to read at arXiv (Cornell University).

Citations
0
Field-weighted impact
1.44
References
17
Authors
6

Abstract

Text-to-motion generation has advanced with diffusion- and flow-based generative models, yet supervised pre-training remains insufficient to align models with high-level objectives such as semantic consistency, realism, and human preference. Existing post-training methods have key limitations: they (1) target a specific motion representation, such as joints, (2) optimize a particular aspect, such as text-motion alignment, and may compromise other factors; and (3) incur substantial computational overhead, data dependence, and coarse-grained optimization. We present a reinforcement fine-tuning framework that comprises a heterogeneous-representation, multi-dimensional reward model, MotionReward, and an efficient, fine-grained fine-tuning method, EasyTune. To obtain a unified semantics representation, MotionReward maps heterogeneous motions into a shared semantic space anchored by text, enabling multi-dimensional reward learning; Self-refinement Preference Learning further enhances semantics without additional annotations. For efficient and effective fine-tuning, we identify the recursive gradient dependence across denoising steps as the key bottleneck, and propose EasyTune, which optimizes step-wise rather than over the full trajectory, yielding dense, fine-grained, and memory-efficient updates. Extensive experiments validate the effectiveness of our framework, achieving FID 0.132 at 22.10 GB peak memory for MLD model and saving up to 15.22 GB over DRaFT. It reduces FID by 22.9% on joint-based ACMDM, and achieves a 12.1% R-Precision gain and 21.7% FID improvement on rotation-based HY-Motion.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Tan, X., Weng, W., Wang, H., Zhao, F., Geng, X., & Wang, L. (2026). MotionRFT: Unified Reinforcement Fine-Tuning for Text-to-Motion Generation. IEEE Transactions on Pattern Analysis and Machine Intelligence, PP, 1–15. https://doi.org/10.1109/tpami.2026.3741371

MLA 9

Tan, Xiaofeng, et al. “MotionRFT: Unified Reinforcement Fine-Tuning for Text-to-Motion Generation.” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. PP, 2026, pp. 1–15. https://doi.org/10.1109/tpami.2026.3741371.

Chicago

Tan, Xiaofeng, Wanjiang Weng, Hongsong Wang, Fang Zhao, Xin Geng, and Liang Wang. 2026. “MotionRFT: Unified Reinforcement Fine-Tuning for Text-to-Motion Generation.” IEEE Transactions on Pattern Analysis and Machine Intelligence PP: 1–15. https://doi.org/10.1109/tpami.2026.3741371.

Harvard

Tan, X. et al. (2026) ‘MotionRFT: Unified Reinforcement Fine-Tuning for Text-to-Motion Generation’, IEEE Transactions on Pattern Analysis and Machine Intelligence, PP, pp. 1–15. doi:10.1109/tpami.2026.3741371.

IEEE

X. Tan, W. Weng, H. Wang, F. Zhao, X. Geng, and L. Wang, “MotionRFT: Unified Reinforcement Fine-Tuning for Text-to-Motion Generation,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. PP, pp. 1–15, 2026, doi: 10.1109/tpami.2026.3741371.

BibTeX

@article{tan2026motionrft,
  title     = {{MotionRFT: Unified Reinforcement Fine-Tuning for Text-to-Motion Generation}},
  author    = {Tan, Xiaofeng and Weng, Wanjiang and Wang, Hongsong and Zhao, Fang and Geng, Xin and Wang, Liang},
  journal   = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year      = {2026},
  volume    = {PP},
  pages     = {1--15},
  doi       = {10.1109/tpami.2026.3741371},
  url       = {https://doi.org/10.1109/tpami.2026.3741371}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Computer Science › Computer Graphics and Computer-Aided Design › Human Motion and Animation

  • text-to-motion generation
  • reinforcement learning fine-tuning
  • diffusion models
  • flow-based generative models
  • reward modeling
  • semantic alignment
  • memory-efficient fine-tuning

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Tan, X., Weng, W., Wang, H., Zhao, F., Geng, X., & Wang, L. (2026). MotionRFT: Unified Reinforcement Fine-Tuning for Text-to-Motion Generation. IEEE Transactions on Pattern Analysis and Machine Intelligence, PP, 1–15. https://doi.org/10.1109/tpami.2026.3741371

How many times has this paper been cited?

0 times, according to OpenAlex on 16 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at arXiv (Cornell University): sign in and open the PDF from this page.

Who wrote this paper?

Xiaofeng Tan, Wanjiang Weng, Hongsong Wang, Fang Zhao, Xin Geng, Liang Wang.

What is the DOI of this paper?

10.1109/tpami.2026.3741371, permanently at https://doi.org/10.1109/tpami.2026.3741371. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 16 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.