taldatech/bair_256
收藏Hugging Face2026-03-06 更新2026-03-29 收录
下载链接：
https://hf-mirror.com/datasets/taldatech/bair_256
下载链接
链接失效反馈官方服务：
资源简介：
---
license: cc-by-sa-4.0
task_categories:
- robotics
---
# Latent Particle World Models (LPWM)
[Project Website](https://taldatech.github.io/lpwm-web) | [Paper](https://huggingface.co/papers/2603.04553) | [GitHub](https://github.com/taldatech/lpwm)
Latent Particle World Model (LPWM) is a self-supervised object-centric world model scaled to real-world multi-object datasets and applicable in decision-making. LPWM autonomously discovers keypoints, bounding boxes, and object masks directly from video data, enabling it to learn rich scene decompositions without supervision. The architecture is trained end-to-end purely from videos and supports flexible conditioning on actions, language, and image goals.
## Sample Usage
To train LPWM on a dataset like Sketchy using the official implementation, you can use the following commands:
```bash
# Install environment
conda env create -f environment.yml
conda activate dlp
# Train LPWM on Sketchy
python train_lpwm.py --dataset sketchy
```
## Citation
```bibtex
@inproceedings{
daniel2026latent,
title={Latent Particle World Models: Self-supervised Object-centric Stochastic Dynamics Modeling},
author={Tal Daniel and Carl Qi and Dan Haramati and Amir Zadeh and Chuan Li and Aviv Tamar and Deepak Pathak and David Held},
booktitle={The Fourteenth International Conference on Learning Representations},
year={2026},
url={https://openreview.net/forum?id=lTaPtGiUUc}
}
```
提供机构：
taldatech
