Image Feature Extraction
Transformers
Safetensors
feature-extraction
vision
image-embeddings
vision-transformer
foundation-model
knowledge-distillation
multi-teacher-distillation
elastic-tokens
token-compression
radio
icml-2026
custom_code
Instructions to use nvidia/C-RADIOv4-1D-H with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nvidia/C-RADIOv4-1D-H with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-feature-extraction", model="nvidia/C-RADIOv4-1D-H", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("nvidia/C-RADIOv4-1D-H", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -252,3 +252,16 @@ Describe the life critical impact (if present). | Not Applicable
|
|
| 252 |
Use Case Restrictions: | Abide by NVIDIA Open Model License Agreement
|
| 253 |
Model and dataset restrictions: | The Principle of least privilege (PoLP) is applied limiting access for dataset generation and model development. Restrictions enforce dataset access during training, and dataset license constraints adhered to.
|
| 254 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 252 |
Use Case Restrictions: | Abide by NVIDIA Open Model License Agreement
|
| 253 |
Model and dataset restrictions: | The Principle of least privilege (PoLP) is applied limiting access for dataset generation and model development. Restrictions enforce dataset access during training, and dataset license constraints adhered to.
|
| 254 |
|
| 255 |
+
## Citation
|
| 256 |
+
|
| 257 |
+
If you use RADIO1D in your research, please cite:
|
| 258 |
+
|
| 259 |
+
```bibtex
|
| 260 |
+
@inproceedings{heinrich2026radio1d,
|
| 261 |
+
title = {{RADIO1D}: Elastic Representations for Condensed Vision Modeling},
|
| 262 |
+
author = {Heinrich, Greg and Ranzinger, Mike and McCarthy, Collin and Bagrov, Natan and Khvedchenya, Eugene and Catanzaro, Bryan and Kautz, Jan and Tao, Andrew and Molchanov, Pavlo},
|
| 263 |
+
booktitle = {Proceedings of the 43rd International Conference on Machine Learning (ICML)},
|
| 264 |
+
year = {2026},
|
| 265 |
+
url = {https://arxiv.org/abs/2607.03624}
|
| 266 |
+
}
|
| 267 |
+
```
|