WorldCrafter: consistent video world model with implicit 3D-aware memory
yshan2u · x · 2026-09-22
WorldCrafter is a new paper proposing a consistent video world model built on implicit 3D-aware memory. By encoding 3D spatial information implicitly into a memory module, the model aims to maintain consistent world state across frames and viewpoints during long video generation. Paper link in the original post.
More from Research
- 37 benchmarks, 130K decisions per model: jev excels at tools and automation — multimodalart · 2026-09-22
- Figure's Helix 2.5 robots complete 56% of tasks in 30 unseen Bay Area homes — lukas_m_ziegler · 2026-09-22
- Decision Index 0.1: leaderboard asks 130K questions to 30+ open decision models — multimodalart · 2026-09-22
- Deep Persona: 3-layer psych-grounded architecture makes LLM role-playing agents more humanlike — UoHaifa · 2026-09-22
- CARE helps VLA robots recover from failures, boosting task success by up to 15.9 points — dalian-university-of-technology · 2026-09-22
- Mira-Scene solves generative 3D scene layout with pixel-aligned coordinate maps, +39.8% 3D-IoU — Yang-Tian Sun · 2026-09-22