🤗 Hugging Face | Paper | Repository
Cosmos-H-Surgical-Predict is a surgical video world foundation model for simulating and predicting future surgical states, part of the Cosmos-H-Surgical suite and the NVIDIA MedTech Open Models.
- [March 16, 2026] As part of the NVIDIA MedTech Open Models, we released Cosmos-H-Surgical-Predict
We introduce Cosmos-H-Surgical-Predict, specialized for simulating and predicting the future state of the world in the form of video. Cosmos-H-Surgical-Predict is a flow based model utilizes Cosmos-Reason1, a Physical AI reasoning vision language model (VLM), as the text encoder. Cosmos-H-Surgical-Predict is built upon the Cosmos-Predict2.5-2B model and is adapted specifically for surgical video data.
Input prompt
real surgery scene: right instrument coagulates the cystic mesentery while left instrument retracts the cystic mesentery.| Input image | Output video |
|---|---|
coagulation.mp4 |
Input prompt
real surgery scene: left needle driver passes needle to right needle driver.| Input Video | Output Video |
|---|---|
needleGrasping.mp4 |
predict2.5.mp4
Our world simulation models, Cosmos-Predict's fundamental capability is predicting future world states in video form supporting multimodal inputs. We have open sourced both pre-trained foundation models as well as post-trained models accelerating multiple domains. Please check back as we continue to add more specialized models and capabilities to the Predict family!
Cosmos-H-Surgical-Predict: Base 2B checkpoints, trained from the ground up for Physical AI and robotics for surgical tasks.
| Model Name | Capability | Input |
|---|---|---|
| Cosmos-H-Surgical-Predict | Base Model | text + image |
We welcome contributions. Check out our Contributing Guide to get started, and share your feedback through issues.
This project will download and install additional third-party open source software projects. Review the license terms of these open source projects before use.
Cosmos-H-Surgical source code is released under the Apache 2 License.
Cosmos-H-Surgical models are released under the NVIDIA License. You are responsible for ensuring that your use of NVIDIA AI Foundation Models complies with all applicable laws.