---
license: cc-by-nc-4.0
base_model: nvidia/Cosmos3-Nano
datasets:
  - Hokin/object-permanence
pipeline_tag: video-to-video
tags:
  - object-permanence
  - world-model
  - video-prediction
  - physical-reasoning
  - cosmos
  - cosmos3
---

# PWM-WROP

A 16B multimodal world model post-trained for **object permanence** in video generation and reasoning.

## License and attribution

The fine-tuned weights in this repository are released under
[CC BY-NC 4.0](https://creativecommons.org/licenses/by-nc/4.0/) — attribution: **Hokin Deng**.
Non-commercial use only. For commercial licensing contact
hokinxqdeng@gmail.com.

**Built on NVIDIA Cosmos.** PWM-WROP is a derivative of the base model nvidia/Cosmos3-Nano
(Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES), which NVIDIA distributes under the
OpenMDW License Agreement 1.1. As that agreement requires, a copy is included here as
[LICENSE-OpenMDW-1.1.txt](LICENSE-OpenMDW-1.1.txt) and NVIDIA's copyright notice is retained; its
terms apply to the base-model portions of these weights, and the CC BY-NC 4.0 terms above apply
to the fine-tuning as released.

## Citation

Paper: *Training Object Permanence in World Models* (arXiv link to follow).