We present GR-2, a state-of-the-art generalist robot agent for versatile and generalizable robot manipulation. GR-2 is first pre-trained on a vast number of Internet videos to capture the dynamics of the world. This large-scale pre-training, involving 38 million video clips and over 50 billion tokens, equips GR-2 with the ability to generalize across a wide range of robotic tasks and environments during subsequent policy learning. Following this, GR-2 is fine-tuned for both video generation and action prediction using robot trajectories. It exhibits impressive multi-task learning capabilities, achieving an average success rate of 97.7% across more than 100 tasks. Moreover, GR-2 demonstrates exceptional generalization to new, previously unseen scenarios, including novel backgrounds, environments, objects, and tasks. Notably, GR-2 scales effectively with model size, underscoring its potential for continued growth and application. Project page: \url{https://gr2-manipulation.github.io}.

中文翻译：

---

GR-2： 具有 Web 规模知识的生成视频-语言-动作模型，用于机器人操作


我们推出了 GR-2，这是一种最先进的通用机器人代理，用于多功能和可通用的机器人操作。GR-2 首先在大量 Internet 视频上进行预训练，以捕捉世界动态。这种大规模的预训练涉及 3800 万个视频剪辑和超过 500 亿个代币，使 GR-2 能够在随后的策略学习中泛化到广泛的机器人任务和环境。在此之后，GR-2 对使用机器人轨迹的视频生成和动作预测进行了微调。它表现出令人印象深刻的多任务学习能力，在 97.7 多项任务中实现了 100% 的平均成功率。此外，GR-2 展示了对新的、以前从未见过的场景的非凡泛化，包括新的背景、环境、对象和任务。值得注意的是，GR-2 可以有效地随模型大小扩展，突显了其持续增长和应用的潜力。项目页面：\url{https://gr2-manipulation.github.io}。