# Thicker and Quicker: A Jumbo Token for Fast Plain Vision Transformers

arXiv: https://arxiv.org/abs/2502.15021 · HTML: https://mlsanity.com/paper/2502.15021/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 74 of its 86 references that are in the map.
- First posted on arXiv 20 Feb 2025.

## Builds on (most cited first, 30 of 74)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [A Time Series is Worth 64 Words: Long-term Forecasting with Transformers](https://mlsanity.com/paper/2211.14730/) (2022)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization](https://mlsanity.com/paper/2006.16241/) (2020)
- [ViViT: A Video Vision Transformer](https://mlsanity.com/paper/2103.15691/) (2021)
- [DUSt3R: Geometric 3D Vision Made Easy](https://mlsanity.com/paper/2312.14132/) (2023)
- [Do ImageNet Classifiers Generalize to ImageNet?](https://mlsanity.com/paper/1902.10811/) (2019)
- [Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts](https://mlsanity.com/paper/2102.08981/) (2021)
- [4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks](https://mlsanity.com/paper/1904.08755/) (2019)
- [Perceiver: General Perception with Iterative Attention](https://mlsanity.com/paper/2103.03206/) (2021)
- [Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model](https://mlsanity.com/paper/2401.09417/) (2024)
- [Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture](https://mlsanity.com/paper/2301.08243/) (2023)
- [Token Merging: Your ViT But Faster](https://mlsanity.com/paper/2210.09461/) (2022)
- [MnasNet: Platform-Aware Neural Architecture Search for Mobile](https://mlsanity.com/paper/1807.11626/) (2018)

## Built on by (most cited first, 4 of 4)

- [Locality-Attending Vision Transformer](https://mlsanity.com/paper/2603.04892/) (2026)
- [LookWhen? Fast Video Recognition by Learning When, Where, and What to Compute](https://mlsanity.com/paper/2605.06809/) (2026)
- [VisionHOPE: Visual Backbones as Self-Modifying Learning Systems](https://mlsanity.com/paper/2609.33325/) (2026)
- [BarcodeMAE+: Rethinking Masked Pretraining and Global Representations for DNA Barcode Foundation Models](https://mlsanity.com/paper/2609.35877/) (2026)

## Abstract (arXiv)

ViTs are general and accurate, and address many tasks, but ViTs are slow, and are not always practical when efficiency is key. Existing methods for faster ViTs design hybrid non-ViT architectures, losing generality, or shrink their tokens, sacrificing accuracy. Many non-ViT architectures are both fast and accurate. Yet, without significant modifications, they cannot do what ViTs can: process other input shapes, pre-train by SOTA self-supervised learning, reduce computation by dropping tokens, and more. We make ViTs faster by reducing patch token width while increasing global token width by adding a new Jumbo token. Our wider Jumbo token is processed by its own wider FFN to increase model capacity. Yet our Jumbo FFN is efficient: it processes a single token, for speed, and its parameters are shared across all layers, for memory. Crucially, our Jumbo is attention-only and non-hierarchical, like a plain ViT, so it is simple, scalable, flexible, and compatible with ViT methods new and old. Jumbo improves over ViT baselines with Registers from Nano to Large scales while maintaining speed/throughput on ImageNet-1K (0.1-13%). Jumbo also improves segmentation (1.9-3.1% on ADE20K), MAE pre-training (4.9% linear probing on ImageNet-1K), test-time adaptation (5.2% on ImageNet-C), and time series modeling. Our Jumbo models even achieve better speed-accuracy trade-offs than specialized non-ViT compute-efficient models, while maintaining plain-ViT compatibility for practicality. Code and weights are available: https://github.com/antofuller/jumbo