Xiaomi-Robotics-1: Scaling Vision-Language-Action Models with over 100K Hours of Real-World Trajectories

• 类型：arxiv
• 标识：2607.15330
• 链接：https://arxiv.org/abs/2607.15330
• 主分类：engineering
• 形态：method
• 被引：8
• 被引来源：Semantic Scholar
• S2被引：8
• 影响力被引：1
• TLDR：Xiao-Robotics-1 serves as a strong robot foundation policy that can be efficiently fine-tuned on complex, dexterous tasks with high data efficiency and across multiple simulation benchmarks, Xiaomi-Robotics-1 outperforms state-of-the-art methods.
• 副分类：multimodal
• 待LLM分类：否
• 标题中文：Xiaomi-Robotics-1：利用超过10万小时真实轨迹数据扩展视觉-语言-动作模型
• TLDR中文：Xiaomi-Robotics-1是一个强大的机器人基础策略，能在复杂灵巧任务上以高数据效率高效微调，并在多个仿真基准上超越SOTA方法。
• 来源文件：
• /inbox/tom/_candidates/2026-07-20-agent-rag-longcontext-candidates.json
• [S2 enrich]