Official implementation of AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
☆43Feb 17, 2026Updated last week
Alternatives and similar repositories for AnchorWeave
Users that are interested in AnchorWeave are comparing it to the libraries listed below
Sorting:
- MLP version of SuperGaussians.☆15Dec 29, 2024Updated last year
- Scaling Zero-Shot Reference-to-Video Generation☆62Dec 11, 2025Updated 2 months ago
- ☆86Feb 4, 2026Updated 3 weeks ago
- CoV: Chain-of-View Prompting for Spatial Reasoning☆51Jan 23, 2026Updated last month
- Spatial Aptitude Training for Multimodal Langauge Models☆24Feb 8, 2026Updated 2 weeks ago
- ☆23Jul 22, 2025Updated 7 months ago
- Official repository for "Vid2World: Crafting Video Diffusion Models to Interactive World Models" (ICLR 2026), https://arxiv.org/abs/2505.…☆41Jan 27, 2026Updated last month
- End2End Virtual Try-on with Visual Reference☆57Nov 19, 2025Updated 3 months ago
- D2E: Scaling Vision-Action Pretraining on Desktop Data for Transfer to Embodied AI [ICLR 2026]☆71Jan 15, 2026Updated last month
- Official repository for the paper "MVP4D: Multi-View Portrait Video Diffusion for Animatable 4D Avatars"☆41Nov 20, 2025Updated 3 months ago
- VerseCrafter: Dynamic Realistic Video World Model with 4D Geometric Control☆315Updated this week
- Orienting Latent Actions for Video World Modeling☆77Feb 11, 2026Updated 2 weeks ago
- LogiCity@NeurIPS'24, D&B track. A multi-agent inductive learning environment for "abstractions".