Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

1-2026

Abstract

Text-to-motion generation, which synthesizes 3D human motions from text inputs, holds immense potential for applications in gaming, film, and robotics. Recently, diffusion-based methods have been shown to generate more diversity and realistic motion. However, there exists a misalignment between text and motion distributions in diffusion models, which leads to semantically inconsistent or low-quality motions. To address this limitation, we propose Reward-guided sampling Alignment (ReAlign), comprising a step-aware reward model to assess alignment quality during the denoising sampling and a reward-guided strategy that directs the diffusion process toward an optimally aligned distribution. This reward model integrates step-aware tokens and combines a text-aligned module for semantic consistency and a motion-aligned module for realism, refining noisy motions at each timestep to balance probability density and alignment. Extensive experiments of both motion generation and retrieval tasks demonstrate that our approach significantly improves text-motion alignment and motion quality compared to existing state-of-the-art methods. Code — https://wengwanjiang.github.io/ReAlign-page

Discipline

Artificial Intelligence and Robotics

Research Areas

Intelligent Systems and Optimization

Areas of Excellence

Digital transformation

Publication

Proceedings of the 40th Annual AAAI Conference on Artificial Intelligence (AAAI‑26), Singapore, January 20-27

First Page

10621

Last Page

10629

Identifier

10.1609/aaai.v40i13.38035

Publisher

ACM

City or Country

New York

Additional URL

https://doi.org/10.1609/aaai.v40i13.38035

Download

Share

COinS