Back Rohan Paul

Rohan Paul· @rohanpaul_ai · X· 2026-11-11 05:34 · 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 · Original

Rohan Paul@rohanpaul_ai

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.

QuoteInstitute of Foundation Models@IFM_AI

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 ↗

05:34 · 2026-11-11 · UTC+8

Found an error? Send a correction