| --- |
| license: apache-2.0 |
| tags: |
| - video-world-model |
| - video-prediction |
| - physical-ai |
| --- |
| |
| # Learning How the World Evolves: Extrapolative Video World Models via Latent Dynamics Reasoning |
|
|
| [](https://lat-dyn-reason.github.io/) |
| [](http://arxiv.org/abs/xxx) |
| [](https://github.com/Lat-Dyn-Reason/Lat-Dyn-Reason) |
| [](https://huggingface.co/datasets/haodongli/LDR) |
| [](https://huggingface.co/haodongli/LDR) |
|
|
| Please visit our [Github Repo](https://github.com/Lat-Dyn-Reason/Lat-Dyn-Reason) for how to use these models. |
|
|
| ## Structure |
|
|
| ``` |
| LDR/ |
| βββ 128x128/ |
| β βββ single_task/{uniform,parabola,collision,looming,bouncing}.pt |
| β βββ joint_task/joint_5task.pt |
| βββ 256x256/ |
| βββ single_task/{uniform,parabola,collision,looming,bouncing}.pt |
| βββ joint_task/joint_5task.pt |
| ``` |
|
|
| ## BibTeX |
|
|
| ``` |
| @article{xxx, |
| title={xxx}, |
| author={xxx}, |
| journal={xxx}, |
| year={xxx} |
| } |
| ``` |
|
|