Qwen-VLA: Unifying Vision-Language-Action Modeling across Tasks, Environments, and Robot Embodiments
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913178900758528 |
|---|---|
| author | Wang, Qiuyue Li, Mingsheng Guan, Jian Ye, Jinhui Xie, Sicheng Liu, Yitao Chen, Junhao Liang, Zhixuan Zhang, Jie Hu, Xintong Huang, Xuhong Lin, Pei Lin, Junyang Liu, Dayiheng Bai, Shuai Zhou, Jingren Zhang, Jiazhao Yuan, Haoqi Zhou, Gengze Yin, Hang Wang, Ye Huang, Yiyang Lei, Zixing Peng, Wujian Chen, Delin Zheng, Yingming Fan, Jingyang Zhuang, Xianwei Zhou, Xin Li, Haoyang Chen, Anzhe Zhang, Tong Liu, Xuejing Sun, Yuchong Chen, Ruizhe Li, Zhaohai Lü, Chenxu Yang, Zhibo Yu, Tao Chen, Xionghui |
| author_facet | Wang, Qiuyue Li, Mingsheng Guan, Jian Ye, Jinhui Xie, Sicheng Liu, Yitao Chen, Junhao Liang, Zhixuan Zhang, Jie Hu, Xintong Huang, Xuhong Lin, Pei Lin, Junyang Liu, Dayiheng Bai, Shuai Zhou, Jingren Zhang, Jiazhao Yuan, Haoqi Zhou, Gengze Yin, Hang Wang, Ye Huang, Yiyang Lei, Zixing Peng, Wujian Chen, Delin Zheng, Yingming Fan, Jingyang Zhuang, Xianwei Zhou, Xin Li, Haoyang Chen, Anzhe Zhang, Tong Liu, Xuejing Sun, Yuchong Chen, Ruizhe Li, Zhaohai Lü, Chenxu Yang, Zhibo Yu, Tao Chen, Xionghui |
| contents | Embodied intelligence is often studied through specialized models for individual tasks such as manipulation or navigation, resulting in fragmented capabilities and limited generalization across tasks, environments, and robot embodiments. In this work, we study whether heterogeneous embodied decision-making problems can be unified within a single vision-language-action model. We present Qwen-VLA, a unified embodied foundation model that extends Qwen's vision-language modeling stack from perception, understanding, and reasoning to continuous action and trajectory generation through a DiT-based action decoder. Qwen-VLA is trained with a large-scale joint pretraining recipe over diverse data sources, including robotics manipulation trajectories, human egocentric demonstrations, synthetic simulation data, vision-and-language navigation data, trajectory-centric supervision, and auxiliary vision-language data. To support multiple robot platforms, we introduce embodiment-aware prompt conditioning, where robot-specific textual descriptions specify the current embodiment and control convention. We further cast manipulation, navigation, and trajectory prediction into a unified action-and-trajectory prediction framework, enabling transferable visual grounding, spatial reasoning, and continuous action generation across robot morphologies, task families, and environments. Experiments on manipulation, navigation, and trajectory-centric benchmarks show consistent multi-task performance and out-of-distribution generalization under variations in scene layout, background, lighting, object configuration, and robot embodiment. Qwen-VLA-Instruct achieves 97.9% on LIBERO, 73.7% on Simpler-WidowX, 86.1%/87.2% on RoboTwin-Easy/Hard, 69.0% OSR on R2R, 59.6% SR on RxR, 76.9% average OOD success in real-world ALOHA experiments, and 26.6% zero-shot success on DOMINO dynamic manipulation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_30280 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Qwen-VLA: Unifying Vision-Language-Action Modeling across Tasks, Environments, and Robot Embodiments Wang, Qiuyue Li, Mingsheng Guan, Jian Ye, Jinhui Xie, Sicheng Liu, Yitao Chen, Junhao Liang, Zhixuan Zhang, Jie Hu, Xintong Huang, Xuhong Lin, Pei Lin, Junyang Liu, Dayiheng Bai, Shuai Zhou, Jingren Zhang, Jiazhao Yuan, Haoqi Zhou, Gengze Yin, Hang Wang, Ye Huang, Yiyang Lei, Zixing Peng, Wujian Chen, Delin Zheng, Yingming Fan, Jingyang Zhuang, Xianwei Zhou, Xin Li, Haoyang Chen, Anzhe Zhang, Tong Liu, Xuejing Sun, Yuchong Chen, Ruizhe Li, Zhaohai Lü, Chenxu Yang, Zhibo Yu, Tao Chen, Xionghui Robotics Artificial Intelligence Computation and Language Embodied intelligence is often studied through specialized models for individual tasks such as manipulation or navigation, resulting in fragmented capabilities and limited generalization across tasks, environments, and robot embodiments. In this work, we study whether heterogeneous embodied decision-making problems can be unified within a single vision-language-action model. We present Qwen-VLA, a unified embodied foundation model that extends Qwen's vision-language modeling stack from perception, understanding, and reasoning to continuous action and trajectory generation through a DiT-based action decoder. Qwen-VLA is trained with a large-scale joint pretraining recipe over diverse data sources, including robotics manipulation trajectories, human egocentric demonstrations, synthetic simulation data, vision-and-language navigation data, trajectory-centric supervision, and auxiliary vision-language data. To support multiple robot platforms, we introduce embodiment-aware prompt conditioning, where robot-specific textual descriptions specify the current embodiment and control convention. We further cast manipulation, navigation, and trajectory prediction into a unified action-and-trajectory prediction framework, enabling transferable visual grounding, spatial reasoning, and continuous action generation across robot morphologies, task families, and environments. Experiments on manipulation, navigation, and trajectory-centric benchmarks show consistent multi-task performance and out-of-distribution generalization under variations in scene layout, background, lighting, object configuration, and robot embodiment. Qwen-VLA-Instruct achieves 97.9% on LIBERO, 73.7% on Simpler-WidowX, 86.1%/87.2% on RoboTwin-Easy/Hard, 69.0% OSR on R2R, 59.6% SR on RxR, 76.9% average OOD success in real-world ALOHA experiments, and 26.6% zero-shot success on DOMINO dynamic manipulation. |
| title | Qwen-VLA: Unifying Vision-Language-Action Modeling across Tasks, Environments, and Robot Embodiments |
| topic | Robotics Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2605.30280 |