Video-Text-to-Text
Transformers
Safetensors
English
qwen3_vl
image-text-to-text
video
long-video
reasoning
tool-calling
agentic-rl
grpo
multimodal
Instructions to use ParaVT/ParaVT-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ParaVT/ParaVT-8B with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForImageTextToText processor = AutoProcessor.from_pretrained("ParaVT/ParaVT-8B") model = AutoModelForImageTextToText.from_pretrained("ParaVT/ParaVT-8B") - Notebooks
- Google Colab
- Kaggle
mwxely commited on
Commit ·
38409d2
1
Parent(s): b3e2ae8
Add arXiv ID 2605.20342 to Paper badge and BibTeX eprint
Browse files
README.md
CHANGED
|
@@ -23,7 +23,7 @@ tags:
|
|
| 23 |
|
| 24 |
<div align="center">
|
| 25 |
|
| 26 |
-
[](
|
| 27 |
[](https://github.com/EvolvingLMMs-Lab/ParaVT)
|
| 28 |
[](https://huggingface.co/datasets/ParaVT/ParaVT-Parquet)
|
| 29 |
[](https://huggingface.co/datasets/ParaVT/ParaVT-Source)
|
|
@@ -74,6 +74,7 @@ If you find ParaVT useful for your research and applications, please cite:
|
|
| 74 |
title={{ParaVT}: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning},
|
| 75 |
author={Zuhao Yang and Kaichen Zhang and Sudong Wang and Keming Wu and Zhongyu Yang and Bo Li and Xiaojuan Qi and Shijian Lu and Xingxuan Li and Lidong Bing},
|
| 76 |
year={2026},
|
|
|
|
| 77 |
archivePrefix={arXiv},
|
| 78 |
primaryClass={cs.CV}
|
| 79 |
}
|
|
|
|
| 23 |
|
| 24 |
<div align="center">
|
| 25 |
|
| 26 |
+
[](https://arxiv.org/abs/2605.20342)
|
| 27 |
[](https://github.com/EvolvingLMMs-Lab/ParaVT)
|
| 28 |
[](https://huggingface.co/datasets/ParaVT/ParaVT-Parquet)
|
| 29 |
[](https://huggingface.co/datasets/ParaVT/ParaVT-Source)
|
|
|
|
| 74 |
title={{ParaVT}: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning},
|
| 75 |
author={Zuhao Yang and Kaichen Zhang and Sudong Wang and Keming Wu and Zhongyu Yang and Bo Li and Xiaojuan Qi and Shijian Lu and Xingxuan Li and Lidong Bing},
|
| 76 |
year={2026},
|
| 77 |
+
eprint={2605.20342},
|
| 78 |
archivePrefix={arXiv},
|
| 79 |
primaryClass={cs.CV}
|
| 80 |
}
|