# Accelerating Vision Transformers with Adaptive Patch Sizes

arXiv: https://arxiv.org/abs/2510.18091 · HTML: https://mlsanity.com/paper/2510.18091/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 70 of its 80 references that are in the map.
- First posted on arXiv 20 Oct 2025.

## Builds on (most cited first, 30 of 70)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [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)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [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)
- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering](https://mlsanity.com/paper/1612.00837/) (2016)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [MMBench: Is Your Multi-modal Model an All-around Player?](https://mlsanity.com/paper/2307.06281/) (2023)
- [Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention](https://mlsanity.com/paper/2006.16236/) (2020)
- [SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing](https://mlsanity.com/paper/1808.06226/) (2018)
- [Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering](https://mlsanity.com/paper/2209.09513/) (2022)
- [Towards VQA Models That Can Read](https://mlsanity.com/paper/1904.08920/) (2019)
- [MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models](https://mlsanity.com/paper/2306.13394/) (2023)
- [Unified Perceptual Parsing for Scene Understanding](https://mlsanity.com/paper/1807.10221/) (2018)
- [Random Erasing Data Augmentation](https://mlsanity.com/paper/1708.04896/) (2017)
- [MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities](https://mlsanity.com/paper/2308.02490/) (2023)
- [Semantic Understanding of Scenes through the ADE20K Dataset](https://mlsanity.com/paper/1608.05442/) (2016)
- [Token Merging: Your ViT But Faster](https://mlsanity.com/paper/2210.09461/) (2022)
- [DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification](https://mlsanity.com/paper/2106.02034/) (2021)
- [CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification](https://mlsanity.com/paper/2103.14899/) (2021)
- [Exploring Plain Vision Transformer Backbones for Object Detection](https://mlsanity.com/paper/2203.16527/) (2022)

## Built on by (most cited first, 13 of 13)

- [Off The Grid: Detection of Primitives for Feed-Forward 3D Gaussian Splatting](https://mlsanity.com/paper/2512.15508/) (2025)
- [DDiT: Dynamic Patch Scheduling for Efficient Diffusion Transformers](https://mlsanity.com/paper/2602.16968/) (2026)
- [TrajTok: Learning Trajectory Tokens enables better Video Understanding](https://mlsanity.com/paper/2602.22779/) (2026)
- [DC-DiT: Adaptive Compute and Elastic Inference for Visual Generation via Dynamic Chunking](https://mlsanity.com/paper/2603.06351/) (2026)
- [Phase-Aligned RoPE for Mixed-Resolution Diffusion Transformer](https://mlsanity.com/paper/2511.19778/) (2025)
- [DVSM: Decoder-only View Synthesis Model Done Right](https://mlsanity.com/paper/2605.29891/) (2026)
- [Video Patch Pruning: Efficient Video Instance Segmentation via Early Token Reduction](https://mlsanity.com/paper/2604.00827/) (2026)
- [Token Warping Helps MLLMs Look from Nearby Viewpoints](https://mlsanity.com/paper/2604.02870/) (2026)
- [MOSAIK: Multi-Patch Content-Aware Spatial Allocation of Image Tokens for Efficient Generation](https://mlsanity.com/paper/2608.05450/) (2026)
- [PACE: A Unified Condense-and-Extract Paradigm for Fast VLM Inference](https://mlsanity.com/paper/2608.27206/) (2026)
- [Variable-Granularity Tokenization for High-Resolution Object Detection](https://mlsanity.com/paper/2608.28706/) (2026)
- [Dynamic Quadtree Tokenization and Transformer for Adaptive Mesh PDE Forecasting](https://mlsanity.com/paper/2610.04044/) (2026)
- [VisionWeave: Weaving Elastic Visual Representations as a Native Capability of MLLMs](https://mlsanity.com/paper/2610.07987/) (2026)

## Abstract (arXiv)

Vision Transformers (ViTs) partition input images into uniformly sized patches regardless of their content, resulting in long input sequence lengths for high-resolution images. We present Adaptive Patch Transformers (APT), which addresses this by using multiple different patch sizes within the same image. APT reduces the total number of input tokens by allocating larger patch sizes in more homogeneous areas and smaller patches in more complex ones. APT achieves a drastic speedup in ViT inference and training, increasing throughput by 40% on ViT-L and 50% on ViT-H while maintaining downstream performance, and can be applied to a previously fine-tuned ViT, converging in as little as 1 epoch. It also significantly reduces training and inference time without loss of performance in high-resolution dense visual tasks, achieving up to 30% faster training and inference in visual QA, object detection, and semantic segmentation.