Original post · AI translation
智能体通过试错学习。代价高昂的是出错。
世界模型把出错转移到模拟中，这正是支持 PAN 2 这类模型的全部理由。
这是一个免费、开放的“以动作为条件的世界模型”。
它接收你描述的动作，并生成最长 20 秒的视频，展示接下来在物理世界中会发生什么。它的新方法是将任务分成 2 步：先由语言模型推演事件如何发展，再由一个 29B 参数的视频模型将其呈现出来。
Original
Agents learn from trial and error. The expensive part is the error. A world model moves the error into simulation, which is the whole case for something like PAN 2. This is a free, open "action-conditioned world model". Takes an action you describe, and generates up to 20 seconds of video showing what would physically happen next. Its new trick is splitting the job in 2: a language model first works out the plot, then a 29B video model renders it.
推出 PAN 2：一个面向物理智能的开放式基础世界模型。
语言模型预测下一个词。PAN 2 预测下一步世界会怎样：每个动作之后会发生什么，并以时间、物理规律和空间为依据。
迈向能够在行动前模拟“如果……会怎样？”的 AI。
更多详情：https://t.co/lUX7igPOiF
Original
Introducing PAN 2: an open foundation world model for physical intelligence. A language model predicts the next word. PAN 2 predicts the next world: what happens after each action, grounded in time, physics and space. Towards AI that simulates “what if?” before it acts. More details: https://t.co/lUX7igPOiF