Salvato in:
| Autori principali: | , , , , , , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2510.11027 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910001538269184 |
|---|---|
| author | Yang, Ganlin Zhang, Tianyi Hao, Haoran Wang, Weiyun Liu, Yibin Wang, Dehui Chen, Guanzhou Cai, Zijian Chen, Junting Su, Weijie Zhou, Wengang Qiao, Yu Dai, Jifeng Pang, Jiangmiao Luo, Gen Wang, Wenhai Mu, Yao Hou, Zhi |
| author_facet | Yang, Ganlin Zhang, Tianyi Hao, Haoran Wang, Weiyun Liu, Yibin Wang, Dehui Chen, Guanzhou Cai, Zijian Chen, Junting Su, Weijie Zhou, Wengang Qiao, Yu Dai, Jifeng Pang, Jiangmiao Luo, Gen Wang, Wenhai Mu, Yao Hou, Zhi |
| contents | While significant research has focused on developing embodied reasoning capabilities using Vision-Language Models (VLMs) or integrating advanced VLMs into Vision-Language-Action (VLA) models for end-to-end robot control, few studies directly address the critical gap between upstream VLM-based reasoning and downstream VLA policy learning. In this work, we take an initial step toward bridging embodied reasoning with VLA policy learning by introducing Vlaser - a Vision-Language-Action Model with synergistic embodied reasoning capability, which is a foundational vision-language model designed to integrate high-level reasoning with low-level control for embodied agents. Built upon the high-quality Vlaser-6M dataset, Vlaser achieves state-of-the-art performance across a range of embodied reasoning benchmarks - including spatial reasoning, embodied grounding, embodied QA, and task planning. Furthermore, we systematically examine how different VLM initializations affect supervised VLA fine-tuning, offering novel insights into mitigating the domain shift between internet-scale pre-training data and embodied-specific policy learning data. Based on these insights, our approach achieves state-of-the-art results on the WidowX benchmark and competitive performance on the Google Robot benchmark. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_11027 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Vlaser: Vision-Language-Action Model with Synergistic Embodied Reasoning Yang, Ganlin Zhang, Tianyi Hao, Haoran Wang, Weiyun Liu, Yibin Wang, Dehui Chen, Guanzhou Cai, Zijian Chen, Junting Su, Weijie Zhou, Wengang Qiao, Yu Dai, Jifeng Pang, Jiangmiao Luo, Gen Wang, Wenhai Mu, Yao Hou, Zhi Computer Vision and Pattern Recognition While significant research has focused on developing embodied reasoning capabilities using Vision-Language Models (VLMs) or integrating advanced VLMs into Vision-Language-Action (VLA) models for end-to-end robot control, few studies directly address the critical gap between upstream VLM-based reasoning and downstream VLA policy learning. In this work, we take an initial step toward bridging embodied reasoning with VLA policy learning by introducing Vlaser - a Vision-Language-Action Model with synergistic embodied reasoning capability, which is a foundational vision-language model designed to integrate high-level reasoning with low-level control for embodied agents. Built upon the high-quality Vlaser-6M dataset, Vlaser achieves state-of-the-art performance across a range of embodied reasoning benchmarks - including spatial reasoning, embodied grounding, embodied QA, and task planning. Furthermore, we systematically examine how different VLM initializations affect supervised VLA fine-tuning, offering novel insights into mitigating the domain shift between internet-scale pre-training data and embodied-specific policy learning data. Based on these insights, our approach achieves state-of-the-art results on the WidowX benchmark and competitive performance on the Google Robot benchmark. |
| title | Vlaser: Vision-Language-Action Model with Synergistic Embodied Reasoning |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2510.11027 |