Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
base_model:
|
| 6 |
+
- Qwen/Qwen2.5-VL-7B-Instruct
|
| 7 |
+
pipeline_tag: video-text-to-text
|
| 8 |
+
tags:
|
| 9 |
+
- multimodal
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# TimeSearch-R-7B
|
| 13 |
+
- **Code:** https://github.com/Time-Search/TimeSearch-R
|
| 14 |
+
- **Paper:** [TimeSearch-R: Adaptive Temporal Search for Long-Form Video Understanding via Self-Verification Reinforcement Learning](https://arxiv.org/abs/2505.14340)
|
| 15 |
+
|
| 16 |
+
## Citation
|
| 17 |
+
|
| 18 |
+
If you find our work helpful, feel free to give us a cite.
|
| 19 |
+
|
| 20 |
+
```
|
| 21 |
+
@article{timesearch-r,
|
| 22 |
+
title={TimeSearch-R: Adaptive Temporal Search for Long-Form Video Understanding via Self-Verification Reinforcement Learning},
|
| 23 |
+
author={Pan, Junwen and Zhang, Qizhe and Zhang, Rui and Lu, Ming and Wan, Xin and Zhang, Yuan and Liu, Chang and She, Qi},
|
| 24 |
+
journal={arXiv preprint arXiv:2511.05489},
|
| 25 |
+
year={2025}
|
| 26 |
+
}
|
| 27 |
+
```
|