Open-UniMo: Towards Unified Motion-Language Understanding and Generation in the Open World

2026-09-13

AI Summary

为解决开放环境中动作-语言模型的交互和生成问题，提出Open-UniMo模型，通过扩展词汇表、引入运动一致的思维链推理及两阶段训练方法来提升跨模态理解和生成能力。

Abstract

Unified motion generation and understanding is crucial for embodied AI systems that can both synthesize and interpret human actions in open-world environments. Existing motion-language models often treat motion as an auxiliary modality of a language model, leading to text-dominated representations and limited cross-modal interaction. Moreover, the next-token prediction paradigm is not naturally suited to long motion sequences, where autoregressive generation may accumulate prediction errors. To address these challenges, we propose Open-UniMo, a unified Large Motion-Language Model (LMLM) trained on million-scale open-world motion-language data. Open-UniMo promotes modality parity by extending Qwen's vocabulary of about 150K text tokens with 64K motion tokens, enabling motion and language to share a unified token space. We further introduce motion-consistent Chain-of-Thought reasoning as an intermediate representation to bridge language semantics and motion dynamics. Open-UniMo is trained with a two-stage pipeline, where supervised fine-tuning establishes CoT-guided bidirectional motion-language mapping and Group Relative Policy Optimization (GRPO) improves semantic alignment while mitigating cumulative errors in autoregressive motion-token generation. To support comprehensive evaluation, we propose Open-MoBench, a VLM-guided benchmark for assessing text-to-motion (T2M) generation, motion-to-text (M2T) understanding, and bidirectional consistency. Extensive experiments show that Open-UniMo achieves state-of-the-art performance on both conventional metrics and Open-MoBench. Furthermore, ablation studies reveal that M2T understanding is not primarily limited by motion-token vocabulary size; instead, coupling M2T with the learnable T2M generation path yields stronger cross-modal representations, demonstrating that generation can facilitate understanding in AR-based motion-language modeling.

Problem

• motion-language models
• cross-modal interaction
• autoregressive generation
• prediction errors

Innovation

• Unified Large Motion-Language Model
• Motion Tokens
• Chain-of-Thought Reasoning
• Group Relative Policy Optimization
• Open-MoBench