ARC Lab (Tencent IEG) & Peking University · Explorable World Model
WorldCrafter
Generates explorable, spatially consistent 3D environments from a single image or text prompt, supporting minute-scale navigation and camera-controlled world generation. Rather than explicit depth or geometric warping it uses a camera-queryable implicit memory, a memory encoder plus pose-conditioned readout, to decide which historical frames inform a new view. Evaluated on 145 scenes and 725 camera trajectories, reporting the highest overall VBench score among tested baselines, though the competitor names weren't stated. Code and a fast weights variant released.
Open the source ↗Similar Video & Animation releases
- UniAction
Bowen Xue, Zizhang Li, Hong-Xing Yu, Jiajun Wu · Unified action world model · Week 45, 2026
- PermaVid
ys-imtech · Text-to-Video · Week 25, 2026
- DreamX World
AMAP / Alibaba · Text-to-Video · Week 25, 2026
- Gemini Omni vs Seedance 2.0 Comparison
Chetaslua · Text-to-Video · Week 20, 2026
- Seoul World Model
KAIST AI, NAVER AI Lab, SNU AIIS · Text-to-Video · Week 12, 2026
- WildActor
Research · Text-to-Video · Week 11, 2026
Published by Quanta AI Labs, an AI agency in India. Browse every week in AI News Weekly.