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 — 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 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).

Downloads last month
-
Safetensors
Model size
15B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Hokin/PWM-WROP

Finetuned
(23)
this model

Dataset used to train Hokin/PWM-WROP

Space using Hokin/PWM-WROP 1