Being-M0.5: A Real-Time Controllable Vision-Language-Motion Model
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911101451501568 |
|---|---|
| author | Cao, Bin Zheng, Sipeng Wang, Ye Xia, Lujie Wei, Qianshan Jin, Qin Liu, Jing Lu, Zongqing |
| author_facet | Cao, Bin Zheng, Sipeng Wang, Ye Xia, Lujie Wei, Qianshan Jin, Qin Liu, Jing Lu, Zongqing |
| contents | Human motion generation has emerged as a critical technology with transformative potential for real-world applications. However, existing vision-language-motion models (VLMMs) face significant limitations that hinder their practical deployment. We identify controllability as a main bottleneck, manifesting in five key aspects: inadequate response to diverse human commands, limited pose initialization capabilities, poor performance on long-term sequences, insufficient handling of unseen scenarios, and lack of fine-grained control over individual body parts. To overcome these limitations, we present Being-M0.5, the first real-time, controllable VLMM that achieves state-of-the-art performance across multiple motion generation tasks. Our approach is built upon HuMo100M, the largest and most comprehensive human motion dataset to date, comprising over 5 million self-collected motion sequences, 100 million multi-task instructional instances, and detailed part-level annotations that address a critical gap in existing datasets. We introduce a novel part-aware residual quantization technique for motion tokenization that enables precise, granular control over individual body parts during generation. Extensive experimental validation demonstrates Being-M0.5's superior performance across diverse motion benchmarks, while comprehensive efficiency analysis confirms its real-time capabilities. Our contributions include design insights and detailed computational analysis to guide future development of practical motion generators. We believe that HuMo100M and Being-M0.5 represent significant advances that will accelerate the adoption of motion generation technologies in real-world applications. The project page is available at https://beingbeyond.github.io/Being-M0.5. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_07863 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Being-M0.5: A Real-Time Controllable Vision-Language-Motion Model Cao, Bin Zheng, Sipeng Wang, Ye Xia, Lujie Wei, Qianshan Jin, Qin Liu, Jing Lu, Zongqing Computer Vision and Pattern Recognition Machine Learning Human motion generation has emerged as a critical technology with transformative potential for real-world applications. However, existing vision-language-motion models (VLMMs) face significant limitations that hinder their practical deployment. We identify controllability as a main bottleneck, manifesting in five key aspects: inadequate response to diverse human commands, limited pose initialization capabilities, poor performance on long-term sequences, insufficient handling of unseen scenarios, and lack of fine-grained control over individual body parts. To overcome these limitations, we present Being-M0.5, the first real-time, controllable VLMM that achieves state-of-the-art performance across multiple motion generation tasks. Our approach is built upon HuMo100M, the largest and most comprehensive human motion dataset to date, comprising over 5 million self-collected motion sequences, 100 million multi-task instructional instances, and detailed part-level annotations that address a critical gap in existing datasets. We introduce a novel part-aware residual quantization technique for motion tokenization that enables precise, granular control over individual body parts during generation. Extensive experimental validation demonstrates Being-M0.5's superior performance across diverse motion benchmarks, while comprehensive efficiency analysis confirms its real-time capabilities. Our contributions include design insights and detailed computational analysis to guide future development of practical motion generators. We believe that HuMo100M and Being-M0.5 represent significant advances that will accelerate the adoption of motion generation technologies in real-world applications. The project page is available at https://beingbeyond.github.io/Being-M0.5. |
| title | Being-M0.5: A Real-Time Controllable Vision-Language-Motion Model |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2508.07863 |