# VRoPE: Rotary Position Embedding for Video Large Language Models

arXiv: https://arxiv.org/abs/2502.11664 · HTML: https://mlsanity.com/paper/2502.11664/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 34 references that are in the map.
- First posted on arXiv 17 Feb 2025.

## Builds on (most cited first, 23 of 23)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [MLP-Mixer: An all-MLP Architecture for Vision](https://mlsanity.com/paper/2105.01601/) (2021)
- [Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis](https://mlsanity.com/paper/2405.21075/) (2024)
- [Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts](https://mlsanity.com/paper/2102.08981/) (2021)
- [Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval](https://mlsanity.com/paper/2104.00650/) (2021)
- [MVBench: A Comprehensive Multi-modal Video Understanding Benchmark](https://mlsanity.com/paper/2311.17005/) (2023)
- [EVA-CLIP: Improved Training Techniques for CLIP at Scale](https://mlsanity.com/paper/2303.15389/) (2023)
- [EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding](https://mlsanity.com/paper/2308.09126/) (2023)
- [LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understanding](https://mlsanity.com/paper/2407.15754/) (2024)
- [LLaVA-Video: Video Instruction Tuning With Synthetic Data](https://mlsanity.com/paper/2410.02713/) (2024)
- [Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding](https://mlsanity.com/paper/2311.08046/) (2023)
- [TempCompass: Do Video LLMs Really Understand Videos?](https://mlsanity.com/paper/2403.00476/) (2024)
- [OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generation](https://mlsanity.com/paper/2407.02371/) (2024)
- [PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning](https://mlsanity.com/paper/2404.16994/) (2024)
- [DenseFusion-1M: Merging Vision Experts for Comprehensive Multimodal Perception](https://mlsanity.com/paper/2407.08303/) (2024)
- [Towards Event-oriented Long Video Understanding](https://mlsanity.com/paper/2406.14129/) (2024)

## Built on by (most cited first, 18 of 18)

- [Revisiting Multimodal Positional Encoding in Vision-Language Models](https://mlsanity.com/paper/2510.23095/) (2025)
- [RoPECraft: Training-Free Motion Transfer with Trajectory-Guided RoPE Optimization on Diffusion Transformers](https://mlsanity.com/paper/2505.13344/) (2025)
- [Breaking the Encoder Barrier for Seamless Video-Language Understanding](https://mlsanity.com/paper/2503.18422/) (2025)
- [Future Forcing: Future-aware Training-free KV Cache Policy for Autoregressive Video Generation](https://mlsanity.com/paper/2605.30083/) (2026)
- [VFRTok: Variable Frame Rates Video Tokenizer with Duration-Proportional Information Assumption](https://mlsanity.com/paper/2505.12053/) (2025)
- [Improving GUI Grounding with Explicit Position-to-Coordinate Mapping](https://mlsanity.com/paper/2510.03230/) (2025)
- [A Circular Argument : Does RoPE need to be Equivariant for Vision?](https://mlsanity.com/paper/2511.08368/) (2025)
- [ViKey: Enhancing Temporal Understanding in Videos via Visual Prompting](https://mlsanity.com/paper/2603.23186/) (2026)
- [Extending Audio Context for Long-Form Understanding in Large Audio-Language Models](https://mlsanity.com/paper/2510.15231/) (2025)
- [4D-RGPT: Toward Region-level 4D Understanding via Perceptual Distillation](https://mlsanity.com/paper/2512.17012/) (2025)
- [Adaptive 3D-RoPE: Physics-Aligned Rotary Positional Encoding for Wireless Foundation Models](https://mlsanity.com/paper/2605.00968/) (2026)
- [DynaTok: Temporally Adaptive and Positional Bias-Aware Token Compression for Video-LLMs](https://mlsanity.com/paper/2605.19322/) (2026)
- [T2SGrid: Temporal-to-Spatial Gridification for Video Temporal Grounding](https://mlsanity.com/paper/2603.06973/) (2026)
- [PiT: Progressive Diffusion Transformer](https://mlsanity.com/paper/2505.13219/) (2025)
- [Diagnostics of cognitive failures in multi-agent expert systems using dynamic evaluation protocols and subsequent mutation of the processing context](https://mlsanity.com/paper/2509.15366/) (2025)
- [AdaSpark: Adaptive Sparsity for Efficient Long-Video Understanding](https://mlsanity.com/paper/2604.08077/) (2026)
- [RIG-RoPE: Relation-Stratified Multimodal Attention with Instance-Local Rotary Geometry and Representation-Aware Traversal Coordinates](https://mlsanity.com/paper/2608.05154/) (2026)
- [MinkowskiPE: Minkowski Positional Encoding for Spatiotemporal Perception](https://mlsanity.com/paper/2609.33804/) (2026)

## Abstract (arXiv)

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.