# Don't Look Twice: Faster Video Transformers with Run-Length Tokenization

arXiv: https://arxiv.org/abs/2411.05222 · HTML: https://mlsanity.com/paper/2411.05222/

## Key facts

- Cited by 43 papers in the map (data through 14 Oct 2026).
- Builds on 49 of its 56 references that are in the map.
- First posted on arXiv 7 Nov 2024.

## Builds on (most cited first, 30 of 49)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [The Kinetics Human Action Video Dataset](https://mlsanity.com/paper/1705.06950/) (2017)
- [SlowFast Networks for Video Recognition](https://mlsanity.com/paper/1812.03982/) (2018)
- [Is Space-Time Attention All You Need for Video Understanding?](https://mlsanity.com/paper/2102.05095/) (2021)
- [ViViT: A Video Vision Transformer](https://mlsanity.com/paper/2103.15691/) (2021)
- [VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training](https://mlsanity.com/paper/2203.12602/) (2022)
- [The "something something" video database for learning and evaluating visual common sense](https://mlsanity.com/paper/1706.04261/) (2017)
- [Two-Stream Convolutional Networks for Action Recognition in Videos](https://mlsanity.com/paper/1406.2199/) (2014)
- [Token Merging: Your ViT But Faster](https://mlsanity.com/paper/2210.09461/) (2022)
- [Multiscale Vision Transformers](https://mlsanity.com/paper/2104.11227/) (2021)
- [WorldSimBench: Towards Video Generation Models as World Simulators](https://mlsanity.com/paper/2410.18072/) (2024)
- [DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification](https://mlsanity.com/paper/2106.02034/) (2021)
- [TSM: Temporal Shift Module for Efficient Video Understanding](https://mlsanity.com/paper/1811.08383/) (2018)
- [GroupViT: Semantic Segmentation Emerges from Text Supervision](https://mlsanity.com/paper/2202.11094/) (2022)
- [VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking](https://mlsanity.com/paper/2303.16727/) (2023)
- [MViTv2: Improved Multiscale Vision Transformers for Classification and Detection](https://mlsanity.com/paper/2112.01526/) (2021)
- [VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text](https://mlsanity.com/paper/2104.11178/) (2021)
- [Masked Autoencoders As Spatiotemporal Learners](https://mlsanity.com/paper/2205.09113/) (2022)
- [Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations](https://mlsanity.com/paper/2202.07800/) (2022)
- [AdaViT: Adaptive Tokens for Efficient Vision Transformer](https://mlsanity.com/paper/2112.07658/) (2021)

## Built on by (most cited first, 30 of 43)

- [VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding](https://mlsanity.com/paper/2501.13106/) (2025)
- [TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos](https://mlsanity.com/paper/2504.17343/) (2025)
- [Visual Planning: Let's Think Only with Images](https://mlsanity.com/paper/2505.11409/) (2025)
- [Dynamic Chunking for End-to-End Hierarchical Sequence Modeling](https://mlsanity.com/paper/2507.07955/) (2025)
- [HoliTom: Holistic Token Merging for Fast Video Large Language Models](https://mlsanity.com/paper/2505.21334/) (2025)
- [LLaVA-OneVision-2: Towards Next-Generation Perceptual Intelligence](https://mlsanity.com/paper/2605.25979/) (2026)
- [Shifting AI Efficiency From Model-Centric to Data-Centric Compression](https://mlsanity.com/paper/2505.19147/) (2025)
- [Improving LLM Video Understanding with 16 Frames Per Second](https://mlsanity.com/paper/2503.13956/) (2025)
- [OmniV-Med: Scaling Medical Vision-Language Model for Universal Visual Understanding](https://mlsanity.com/paper/2504.14692/) (2025)
- [AsymRnR: Video Diffusion Transformers Acceleration with Asymmetric Reduction and Restoration](https://mlsanity.com/paper/2412.11706/) (2024)
- [Multimodal Medical Code Tokenizer](https://mlsanity.com/paper/2502.04397/) (2025)
- [Accelerating Vision Transformers with Adaptive Patch Sizes](https://mlsanity.com/paper/2510.18091/) (2025)
- [OneVision-Encoder: Codec-Aligned Sparsity as a Foundational Principle for Multimodal Intelligence](https://mlsanity.com/paper/2602.08683/) (2026)
- [Causality Matters: How Temporal Information Emerges in Video Language Models](https://mlsanity.com/paper/2508.11576/) (2025)
- [One Trajectory, One Token: Grounded Video Tokenization via Panoptic Sub-object Trajectory](https://mlsanity.com/paper/2505.23617/) (2025)
- [LongVideo-R1: Smart Navigation for Low-cost Long Video Understanding](https://mlsanity.com/paper/2602.20913/) (2026)
- [Bootstrap Your Own Views: Masked Ego-Exo Modeling for Fine-grained View-invariant Video Representations](https://mlsanity.com/paper/2503.19706/) (2025)
- [PyramidalWan: On Making Pretrained Video Model Pyramidal for Efficient Inference](https://mlsanity.com/paper/2601.04792/) (2026)
- [PixelPrune: Pixel-Level Adaptive Visual Token Reduction via Predictive Coding](https://mlsanity.com/paper/2604.00886/) (2026)
- [Hydraulis: Balancing Large Transformer Model Training via Co-designing Parallel Strategies and Data Assignment](https://mlsanity.com/paper/2412.07894/) (2024)
- [Top-Down Compression: Revisit Efficient Vision Token Projection for Visual Instruction Tuning](https://mlsanity.com/paper/2505.11945/) (2025)
- [LET-US: Long Event-Text Understanding of Scenes](https://mlsanity.com/paper/2508.07401/) (2025)
- [Revisiting MLLM Token Technology through the Lens of Classical Visual Coding](https://mlsanity.com/paper/2508.13460/) (2025)
- [TrajTok: Learning Trajectory Tokens enables better Video Understanding](https://mlsanity.com/paper/2602.22779/) (2026)
- [Towards Fast, Memory-based and Data-Efficient Vision-Language Policy](https://mlsanity.com/paper/2503.10322/) (2025)
- [QLIP: A Dynamic Quadtree Vision Prior Enhances MLLM Performance Without Retraining](https://mlsanity.com/paper/2505.23004/) (2025)
- [Compression Tells Intelligence: Visual Coding, Visual Token Technology, and the Unification](https://mlsanity.com/paper/2601.20742/) (2026)
- [Static or Dynamic: Towards Query-Adaptive Token Selection for Video Question Answering](https://mlsanity.com/paper/2504.21403/) (2025)
- [VSI: Visual Subtitle Integration for Keyframe Selection to enhance Long Video Understanding](https://mlsanity.com/paper/2508.06869/) (2025)
- [Video Compression Meets Video Generation: Latent Inter-Frame Pruning with Attention Recovery](https://mlsanity.com/paper/2603.05811/) (2026)

## Abstract (arXiv)

Transformers are slow to train on videos due to extremely large numbers of input tokens, even though many video tokens are repeated over time. Existing methods to remove such uninformative tokens either have significant overhead, negating any speedup, or require tuning for different datasets and examples. We present Run-Length Tokenization (RLT), a simple approach to speed up video transformers inspired by run-length encoding for data compression. RLT efficiently finds and removes runs of patches that are repeated over time prior to model inference, then replaces them with a single patch and a positional encoding to represent the resulting token's new length. Our method is content-aware, requiring no tuning for different datasets, and fast, incurring negligible overhead. RLT yields a large speedup in training, reducing the wall-clock time to fine-tune a video transformer by 30% while matching baseline model performance. RLT also works without any training, increasing model throughput by 35% with only 0.1% drop in accuracy. RLT speeds up training at 30 FPS by more than 100%, and on longer video datasets, can reduce the token count by up to 80%. Our project page is at https://rccchoudhury.github.io/projects/rlt/.