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
- Six years later, a blogger unboxes a brand-new-in-box Microsoft Surface Duo — revodavid · 2026-09-10
- Surgical robots matter more for China's future than humanoid robots, argues poster — PAstynome · 2026-09-10
- Medtronic Invests $700M in Chinese Surgical Robot Startup Cornerstone — PAstynome · 2026-09-10
- iPhone 18 Pro's variable aperture: Apple returns to physics after hitting compute wall — r0ck3t23 · 2026-09-10
- kevin_zakka releases mjbatch to run thousands of MuJoCo sims in parallel on CPU — KyleMorgenstein · 2026-09-10
- UISEE's AI Driver Subscriptions Grow 6x, Now 15.4% of Revenue as It Joins Stock Connect — 创业邦 · 2026-09-10