aifollow.news
Back Rohan Paul
Rohan Paul· @rohanpaul_ai · X· · Original publication time AI score47

PAN 2 introduced as an open world model that generates up to 20 seconds of video from an actionMachine translation

AI introduction

PAN 2 is described as a free, open action-conditioned world model. Given a described action, it generates up to 20 seconds of video showing what might physically happen next. A language model works out the plot before a 29B video model renders it.

Original post · AI translation

@rohanpaul_ai
Translation · refer to the original

智能体通过试错学习。代价高昂的部分是犯错。 世界模型把犯错的过程移入模拟,这正是 PAN 2 这样的模型存在的全部理由。

这是一个免费、开放的“以动作为条件的世界模型”。

它接收你描述的一个动作,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。它的新做法是把任务分成 2 步:先由一个语言模型推演情节,再由一个 29B 参数的视频模型将其渲染出来。

QuoteInstitute of Foundation Models@IFM_AI
Translation
隆重推出 PAN 2:一个面向物理智能的开放基础世界模型。 语言模型预测下一个词。PAN 2 预测接下来的世界:每个动作之后会发生什么,其预测以时间、物理规律和空间为依据。 迈向会在行动前模拟“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

View this post on X ↗

Source: Rohan Paul · x.com

Model
Found an error? Send a correction