Offering great potential in robotic manipulation, a capable Vision-Language-Action (VLA) foundation model is expected to faithfully generalize across tasks and platforms while ensuring cost efficiency (e.g., data and GPU hours required for adaptation). To this end, we develop LingBot-VLA with around 20,000 hours of real-world data from 9 popular dual-arm robot configurations. Through a systematic assessment on 3 robotic platforms, each completing 100 tasks with 130 post-training episodes per task, our model achieves clear superiority over competitors, showcasing its strong performance and broad generalizability. We have also built an efficient codebase, which delivers a throughput of 261 samples per second per GPU with an 8-GPU training setup, representing a 1.5~2.8$\times$ (depending on the relied VLM base model) speedup over existing VLA-oriented codebases. The above features ensure that our model is well-suited for real-world deployment. To advance the field of robot learning, we provide open access to the code, base model, and benchmark data, with a focus on enabling more challenging tasks and promoting sound evaluation standards.

翻译：具备卓越潜能的视觉-语言-动作基础模型，有望在确保成本效益（例如适应过程所需的数据与GPU时数）的同时，可靠地泛化至不同任务与平台。为此，我们利用来自9种主流双机械臂配置、总计约20,000小时的真实世界数据，开发了LingBot-VLA模型。通过在3种机器人平台上进行系统评估（每个平台完成100项任务，每项任务包含130次训练后测试），本模型展现出相较于同类方案的显著优势，体现了其强劲性能与广泛泛化能力。我们还构建了高效代码库，在8-GPU训练配置下可实现每秒每GPU处理261个样本的吞吐量，相比现有面向VLA的代码库实现了1.5~2.8倍（具体倍数取决于所依托的视觉语言基础模型）的加速效果。上述特性确保本模型能充分适应实际部署需求。为推进机器人学习领域发展，我们公开提供代码、基础模型与基准数据，致力于支持更具挑战性的任务开发并推动健全的评估标准建立。