MoRL: Reinforced Reasoning for Unified Motion Understanding and Generation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911450095681536 |
|---|---|
| author | Wang, Hongpeng Zhang, Zeyu Li, Wenhao Tang, Hao |
| author_facet | Wang, Hongpeng Zhang, Zeyu Li, Wenhao Tang, Hao |
| contents | Human motion understanding and generation are crucial for vision and robotics but remain limited in reasoning capability and test-time planning. We propose MoRL, a unified multimodal motion model trained with supervised fine-tuning and reinforcement learning with verifiable rewards. Our task-specific reward design combines semantic alignment and reasoning coherence for understanding with physical plausibility and text-motion consistency for generation, improving both logical reasoning and perceptual realism. To further enhance inference, we introduce Chain-of-Motion (CoM), a test-time reasoning method that enables step-by-step planning and reflection. We also construct two large-scale CoT datasets, MoUnd-CoT-140K and MoGen-CoT-140K, to align motion sequences with reasoning traces and action descriptions. Experiments on HumanML3D and KIT-ML show that MoRL achieves significant gains over state-of-the-art baselines. Code: https://github.com/AIGeeksGroup/MoRL. Website: https://aigeeksgroup.github.io/MoRL. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_14534 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | MoRL: Reinforced Reasoning for Unified Motion Understanding and Generation Wang, Hongpeng Zhang, Zeyu Li, Wenhao Tang, Hao Computer Vision and Pattern Recognition Human motion understanding and generation are crucial for vision and robotics but remain limited in reasoning capability and test-time planning. We propose MoRL, a unified multimodal motion model trained with supervised fine-tuning and reinforcement learning with verifiable rewards. Our task-specific reward design combines semantic alignment and reasoning coherence for understanding with physical plausibility and text-motion consistency for generation, improving both logical reasoning and perceptual realism. To further enhance inference, we introduce Chain-of-Motion (CoM), a test-time reasoning method that enables step-by-step planning and reflection. We also construct two large-scale CoT datasets, MoUnd-CoT-140K and MoGen-CoT-140K, to align motion sequences with reasoning traces and action descriptions. Experiments on HumanML3D and KIT-ML show that MoRL achieves significant gains over state-of-the-art baselines. Code: https://github.com/AIGeeksGroup/MoRL. Website: https://aigeeksgroup.github.io/MoRL. |
| title | MoRL: Reinforced Reasoning for Unified Motion Understanding and Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2602.14534 |