Vlaser：具有协同具身推理能力的视觉-语言-动作模型
Vlaser: Vision-Language-Action Model with Synergistic Embodied Reasoning
AI总结：
Vlaser通过整合高级推理与低级控制，解决了具身推理与VLA策略学习之间的关键差距，在多个基准测试中取得最佳性能。
摘要：
尽管已有大量研究致力于通过视觉-语言模型（VLMs）开发具身推理能力，或将其整合到视觉-语言-动作（VLA）模型中以实现端到端的机器人控制，但很少有研究直接解决上游基于VLM的推理与下游VLA策略学习之间的关键差距。在本工作中，我们首次尝试弥合具身推理与VLA策略学习之间的鸿沟，引入了Vlaser——一个具有协同具身推理能力的视觉-语言-动作模型，这是一个基础的视觉-语言模型，旨在将高级推理与低级控制整合到具身智能体中。基于高质量的Vlaser-6M数据集，Vlaser在一系列具身推理基准测试中均取得了最先进的性能，包括空间推理、具身定位、具身问答和任务规划。此外，我们系统地考察了不同VLM初始化对监督VLA微调的影响，提供了新的见解，以缓解互联网级预训练数据与具身特定策略学习数据之间的领域转移问题。基于这些见解，我们的方法在WidowX基准测试中取得了最先进的结果，并在Google Robot基准测试中取得了具有竞争力的性能。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
