@inproceedings{liu-etal-2025-vrope,
    title = "{VR}o{PE}: Rotary Position Embedding for Video Large Language Models",
    author = "Liu, Zikang  and
      Guo, Longteng  and
      Tang, Yepeng  and
      Yue, Tongtian  and
      Cai, Junxian  and
      Ma, Kai  and
      Liu, Qingbin  and
      Chen, Xi  and
      Liu, Jing",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.731/",
    pages = "14471--14483",
    ISBN = "979-8-89176-332-6",
    abstract = "Rotary Position Embedding (RoPE) has shown strong performance in text-based Large Language Models (LLMs), but extending it to video remains a challenge due to the intricate spatiotemporal structure of video frames. Existing adaptations, such as RoPE-3D, attempt to encode spatial and temporal dimensions separately but suffer from two major limitations: positional bias in attention distribution and disruptions in video-text transitions. To overcome these issues, we propose Video Rotary Position Embedding (VRoPE), a novel positional encoding method tailored for Video-LLMs. Specifically, we introduce a more balanced encoding strategy that mitigates attention biases, ensuring a more uniform distribution of spatial focus. Additionally, our approach restructures positional indices to ensure a smooth transition between video and text tokens. Extensive experiments on different models demonstrate that VRoPE consistently outperforms previous RoPE variants, achieving significant improvements in video understanding, temporal reasoning, and retrieval tasks. Code is available at https://github.com/johncaged/VRoPE."
}