Video-Text-to-Text
Transformers
TensorBoard
Safetensors
4DThinker
dynamic-spatial-reasoning
vision-language-model
latent-reasoning
Instructions to use jankin123/4DThinker-3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use jankin123/4DThinker-3B with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("jankin123/4DThinker-3B", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -62,6 +62,18 @@ model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
|
|
| 62 |
processor = AutoProcessor.from_pretrained("./model/4drl")
|
| 63 |
```
|
| 64 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 65 |
## License
|
| 66 |
|
| 67 |
Apache License 2.0
|
|
|
|
| 62 |
processor = AutoProcessor.from_pretrained("./model/4drl")
|
| 63 |
```
|
| 64 |
|
| 65 |
+
## Bibtex
|
| 66 |
+
If you find 4DThinker helpful for your work, please cite
|
| 67 |
+
|
| 68 |
+
```
|
| 69 |
+
@article{chen20264dthinker,
|
| 70 |
+
title={4DThinker: Thinking with 4D Imagery for Dynamic Spatial Understanding},
|
| 71 |
+
author={Chen, Zhangquan and Zhang, Manyuan and Yu, Xinlei and An, Xiang and Li, Bo and Xie, Xin and Wang, ZiDong and Sun, Mingze and Chen, Shuang and Li, Hongyu and others},
|
| 72 |
+
journal={arXiv preprint arXiv:2605.05997},
|
| 73 |
+
year={2026}
|
| 74 |
+
}
|
| 75 |
+
```
|
| 76 |
+
|
| 77 |
## License
|
| 78 |
|
| 79 |
Apache License 2.0
|