VQV Signal

ROBOTS & HARDWARE WATCH TECHNICAL

MBZUAI's Institute of Foundation Models releases PAN 2, an open world model

According to a post on X by @mbzuai, MBZUAI's Institute of Foundation Models has released PAN 2, an open foundation world model that predicts and simulates the physical world so agents can explore the outcomes of actions before taking them. The release includes model weights plus training and inference code. Hao AI Lab announced day-0 support in FastVideo and said PAN 2 simulates 20 seconds in about 2 minutes on eight B300 GPUs.

Source: Scobleizer News Pulse (X) · x.com Found via Robert Scoble’s Scobleizer News Pulse · a post on X, not independently verified Published 2026-11-10T17:40:00+00:00 Detected 2026-11-11T02:21:17+00:00
View original source

According to a post on X by @mbzuai, MBZUAI's Institute of Foundation Models has released PAN 2, an open foundation world model that predicts and simulates the physical world so agents can explore the outcomes of actions before taking them. The release includes model weights plus training and inference code. Hao AI Lab announced day-0 support in FastVideo and said PAN 2 simulates 20 seconds in about 2 minutes on eight B300 GPUs.

AI-assisted summary based on the listed source.

MBZUAI says PAN 2 is an open foundation world model that predicts and simulates the physical world so agents can explore the outcomes of actions before taking them, released with model weights plus training and inference code. Hao AI Lab announced day-0 support in FastVideo, saying PAN 2 simulates 20 seconds in...

Because the weights and code are published, researchers and developers can inspect, run and adapt the model themselves. Teams building agents that plan physical actions may want to compare the reported speed on eight B300 GPUs with their own hardware. The next thing to watch is how PAN 2 performs in independent testing outside the announcements.

Hardware and robotics watchers may want to track whether this becomes a product, benchmark, or deployment signal.

Signal Strength 88% Technical label WATCH Public Interest 42 Category ROBOTS & HARDWARE Reader Depth TECHNICAL

Signal Strength reflects source quality, relevance, freshness and evidence. Public Interest helps organize discovery; it is not proof of truth.

Public Interest components
Recognizable Entity Score 0 Practical Impact Score 36 Novelty Interest Score 94 Consequence Score 30 Curiosity Score 64 Shareability Score 51

VQV surfaced this signal because it is recent, relevant to AI Chips, connected to Scobleizer News Pulse (X).