Vlaser: Vision-Language-Action Model with Synergistic Embodied Reasoning
University of Science and Technology of China · Zhejiang University; Shanghai Artificial Intelligence Laboratory · Carnegie Mellon University · Fudan University · Northeastern University · Shanghai Jiaotong University · Shanghai AI Laboratory, Shanghai Jiaotong University · Shenzhen University · national university of singaore, National University of Singapore · Shanghai Aritifcal Intelligence Laboratory · Tsinghua University, Tsinghua University · Shanghai AI Laboratory · Shanghai Jiao Tong University · Shanghai Artificial Intelligence Laboratory
PDF 由论文原始站点提供，PaperCompass 不保存论文文件。
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 **V**ision-**L**anguage-**A**ction Model with **s**ynergistic **e**mbodied **r**easoning 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. We will open-source the model weights, data generation pipelines, and the full dataset to support future research.