---
# For reference on model card metadata, see the spec: https://github.com/huggingface/hub-docs/blob/main/modelcard.md?plain=1
# Doc / guide: https://huggingface.co/docs/hub/model-cards
{}
---
# 🤖 Neural Motion Simulator

Official release of the model checkpoints from the paper:  
**[Neural Motion Simulator: Pushing the Limit of World Models in Reinforcement Learning](https://arxiv.org/pdf/2504.07095)**   

The released model consists of two parts: the main world model (MoSim model) and a flow model used to implement the functionality described in Section 3.7 of the paper.
All MoSim models are trained exclusively on data collected from random policies.
---