OneTwoVLA: A Unified Vision-Language-Action Model with Adaptive Reasoning
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_ | 1866912933110349824 |
|---|---|
| author | Lin, Fanqi Nai, Ruiqian Hu, Yingdong You, Jiacheng Zhao, Junming Gao, Yang |
| author_facet | Lin, Fanqi Nai, Ruiqian Hu, Yingdong You, Jiacheng Zhao, Junming Gao, Yang |
| contents | General-purpose robots capable of performing diverse tasks require synergistic reasoning and acting capabilities. However, recent dual-system approaches, which separate high-level reasoning from low-level acting, often suffer from challenges such as limited mutual understanding of capabilities between systems and latency issues. This paper introduces OneTwoVLA, a single unified vision-language-action model that can perform both acting (System One) and reasoning (System Two). Crucially, OneTwoVLA adaptively switches between two modes: explicitly reasoning at critical moments during task execution, and generating actions based on the most recent reasoning at other times. To further unlock OneTwoVLA's reasoning and generalization capabilities, we design a scalable pipeline for synthesizing embodied reasoning-centric vision-language data, used for co-training with robot data. We validate OneTwoVLA's effectiveness through extensive experiments, highlighting its superior performance across four key capabilities: long-horizon task planning, error detection and recovery, natural human-robot interaction, and generalizable visual grounding, enabling the model to perform long-horizon, highly dexterous manipulation tasks such as making hotpot or mixing cocktails. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_11917 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | OneTwoVLA: A Unified Vision-Language-Action Model with Adaptive Reasoning Lin, Fanqi Nai, Ruiqian Hu, Yingdong You, Jiacheng Zhao, Junming Gao, Yang Robotics General-purpose robots capable of performing diverse tasks require synergistic reasoning and acting capabilities. However, recent dual-system approaches, which separate high-level reasoning from low-level acting, often suffer from challenges such as limited mutual understanding of capabilities between systems and latency issues. This paper introduces OneTwoVLA, a single unified vision-language-action model that can perform both acting (System One) and reasoning (System Two). Crucially, OneTwoVLA adaptively switches between two modes: explicitly reasoning at critical moments during task execution, and generating actions based on the most recent reasoning at other times. To further unlock OneTwoVLA's reasoning and generalization capabilities, we design a scalable pipeline for synthesizing embodied reasoning-centric vision-language data, used for co-training with robot data. We validate OneTwoVLA's effectiveness through extensive experiments, highlighting its superior performance across four key capabilities: long-horizon task planning, error detection and recovery, natural human-robot interaction, and generalizable visual grounding, enabling the model to perform long-horizon, highly dexterous manipulation tasks such as making hotpot or mixing cocktails. |
| title | OneTwoVLA: A Unified Vision-Language-Action Model with Adaptive Reasoning |
| topic | Robotics |
| url | https://arxiv.org/abs/2505.11917 |