metadata
license: apache-2.0
language:
- en
base_model:
- Qwen/Qwen2.5-VL-7B-Instruct
pipeline_tag: video-text-to-text
tags:
- multimodal
TimeSearch-R-7B
- Code: https://github.com/Time-Search/TimeSearch-R
- Paper: TimeSearch-R: Adaptive Temporal Search for Long-Form Video Understanding via Self-Verification Reinforcement Learning
Citation
If you find our work helpful, feel free to give us a cite.
@article{timesearch-r,
title={TimeSearch-R: Adaptive Temporal Search for Long-Form Video Understanding via Self-Verification Reinforcement Learning},
author={Pan, Junwen and Zhang, Qizhe and Zhang, Rui and Lu, Ming and Wan, Xin and Zhang, Yuan and Liu, Chang and She, Qi},
journal={arXiv preprint arXiv:2511.05489},
year={2025}
}