Puffin-World: unified world model with native 3D states, open-sourced with 16M dataset
ccloy · x · 2026-09-10
Researchers from NTU S-Lab, University of Michigan, Beijing Jiaotong University and ACE Robotics released Puffin-World, a unified multimodal world model representing the physical world via three native states—physics, geometry and appearance—unifying gravity-aware camera understanding, free-viewpoint simulation, 3D world generation/reconstruction and closed-loop exploration in one model. The open release includes code, models and the Puffin-16M dataset: 15M vision-language-camera triplets, 1M camera trajectories, and camera-grounded annotations for 44.5M images across 28 public datasets. An interactive demo lets users explore generated worlds with appearance, gravity and dense depth side by side.
More from Embodied
- ROS names Alejandro Hernández Cordero new project lead, eyes 2027 release — ___Mufasaa · 2026-10-27
- ROS Meetup coming to Google's NYC office Oct 29 with speakers from Tangent, Cohesive Robotics, Intrinsic — kscottz · 2026-10-27
- Tesla officially expands robotaxi service area across much of Houston, Texas — Polymarket · 2026-10-27
- Walden Robotics teaches robots to call for help, blending remote assist with autonomy — adnothing · 2026-10-27
- Folding-screen hinges: dozens of ultra-precise parts, one grain of sand can kill the panel — BenBajarin · 2026-10-27
- No π0 weights changed: Motoniq layer lifts real-robot precision fitting from 0/10 to 9/10 — hbouammar · 2026-10-27