VST Training Data

Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously

📄 Paper | 🌐 Project Page | 💻 Code | 🤗 Models

This dataset contains the full training data used for Video Streaming Thinking (VST), including both supervised fine-tuning (SFT) and reinforcement learning (RL) stages.

Dataset Structure

Also available on ModelScope.

Models Trained on This Data

Citation

@article{guan2026videostreamingthinking,
      title={Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously},
      author={Yiran Guan and Liang Yin and Dingkang Liang and Jianzhong Ju and Zhenbo Luo and Jian Luan and Yuliang Liu and Xiang Bai},
      journal={arXiv preprint arXiv:2603.12262},
      year={2026},
}