Abstract
Efficient action generation in vision-language-action (VLA) models requires capturing both coarse action structure and fine-grained details. Discrete action tokens provide compact structural representations but sacrifice precision, while continuous action tokens offer high precision but often require multiple denoising steps. We introduce Discrete Forcing, a flow-matching framework that combines these representations through an explicit coarse-to-fine generation process. It first predicts discrete action tokens to establish a coarse action structure, then uses them to guide continuous action refinement. The discrete and continuous components share a common diffusion transformer backbone with specialized branches, maintaining a parameter count comparable to a conventional single-branch model while requiring only one forward pass per branch. Extensive evaluations across multiple benchmarks demonstrate improved performance and faster inference over a parameter-matched continuous action expert, with consistent performance gains as model capacity increases. Real-world experiments further demonstrate improvements on high-precision and dynamic manipulation tasks.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Wang, J., Song, W., Yu, W., Zhao, H., Wang, X., Chen, J., Wang, D., Wang, Y., & Li, H. (2026). Discrete Forcing: Infusing Discrete Guidance into Continuous Denoising for Few-Step Action Experts. https://omanscience.com/en/articles/discrete-forcing-infusing-discrete-guidance-into-continuous-denoising-for-few-step-action-experts
MLA 9
Wang, Jingbo, et al. "Discrete Forcing: Infusing Discrete Guidance into Continuous Denoising for Few-Step Action Experts." https://omanscience.com/en/articles/discrete-forcing-infusing-discrete-guidance-into-continuous-denoising-for-few-step-action-experts.
Chicago (author–date)
Wang, Jingbo, Wenxuan Song, Wenhao Yu, Han Zhao, Xi Wang, Jiayi Chen, Donglin Wang, Yan Wang, and Haoang Li. 2026. "Discrete Forcing: Infusing Discrete Guidance into Continuous Denoising for Few-Step Action Experts." https://omanscience.com/en/articles/discrete-forcing-infusing-discrete-guidance-into-continuous-denoising-for-few-step-action-experts.
Harvard
Wang, J., Song, W., Yu, W., Zhao, H., Wang, X., Chen, J., Wang, D., Wang, Y. and Li, H. (2026) 'Discrete Forcing: Infusing Discrete Guidance into Continuous Denoising for Few-Step Action Experts', Available at: https://omanscience.com/en/articles/discrete-forcing-infusing-discrete-guidance-into-continuous-denoising-for-few-step-action-experts.
Vancouver
Wang J, Song W, Yu W, Zhao H, Wang X, Chen J, et al. Discrete Forcing: Infusing Discrete Guidance into Continuous Denoising for Few-Step Action Experts. https://omanscience.com/en/articles/discrete-forcing-infusing-discrete-guidance-into-continuous-denoising-for-few-step-action-experts
IEEE
J. Wang, W. Song, W. Yu, H. Zhao, X. Wang, J. Chen, D. Wang, Y. Wang, and H. Li, "Discrete Forcing: Infusing Discrete Guidance into Continuous Denoising for Few-Step Action Experts," https://omanscience.com/en/articles/discrete-forcing-infusing-discrete-guidance-into-continuous-denoising-for-few-step-action-experts.