English
Related papers

Related papers: Accelerating Transformers with Spectrum-Preserving…

200 papers

Masked image modeling (MIM) has emerged as a promising approach for pre-training Vision Transformers (ViTs). MIMs predict masked tokens token-wise to recover target signals that are tokenized from images or generated by pre-trained models…

Computer Vision and Pattern Recognition · Computer Science 2025-03-24 Taekyung Kim , Byeongho Heo , Dongyoon Han

Video transformer models require huge amounts of compute resources due to the spatio-temporal scaling of the input. Tackling this, recent methods have proposed to drop or merge tokens for image models, whether randomly or via learned…

Computer Vision and Pattern Recognition · Computer Science 2025-10-24 Sam Pollard , Michael Wray

Mixup is a commonly adopted data augmentation technique for image classification. Recent advances in mixup methods primarily focus on mixing based on saliency. However, many saliency detectors require intense computation and are especially…

Computer Vision and Pattern Recognition · Computer Science 2022-10-17 Hyeong Kyu Choi , Joonmyung Choi , Hyunwoo J. Kim

Mixture of Experts (MoE) models based on Transformer architecture are pushing the boundaries of language and vision tasks. The allure of these models lies in their ability to substantially increase the parameter count without a…

Mixture of Experts (MoE) models have emerged as the de facto architecture for scaling up language models without significantly increasing the computational cost. Recent MoE models demonstrate a clear trend towards high expert granularity…

Machine Learning · Computer Science 2026-03-30 Wentao Guo , Mayank Mishra , Xinle Cheng , Ion Stoica , Tri Dao

We present DyMU, an efficient, training-free framework that dynamically reduces the computational burden of vision-language models (VLMs) while maintaining high task performance. Our approach comprises two key components. First, Dynamic…

Computer Vision and Pattern Recognition · Computer Science 2025-05-13 Zhenhailong Wang , Senthil Purushwalkam , Caiming Xiong , Silvio Savarese , Heng Ji , Ran Xu

Diffusion transformers have shown significant effectiveness in both image and video synthesis at the expense of huge computation costs. To address this problem, feature caching methods have been introduced to accelerate diffusion…

Machine Learning · Computer Science 2025-02-20 Chang Zou , Xuyang Liu , Ting Liu , Siteng Huang , Linfeng Zhang

Vision Transformers (ViTs) achieve state-of-the-art performance in semantic segmentation but are hindered by high computational and memory costs. To address this, we propose STEP (SuperToken and Early-Pruning), a hybrid token-reduction…

Computer Vision and Pattern Recognition · Computer Science 2026-05-21 Michal Szczepanski , Martyna Poreba , Karim Haroun

Mixup-based augmentation has been found to be effective for generalizing models during training, especially for Vision Transformers (ViTs) since they can easily overfit. However, previous mixup-based methods have an underlying prior…

Computer Vision and Pattern Recognition · Computer Science 2021-11-19 Jie-Neng Chen , Shuyang Sun , Ju He , Philip Torr , Alan Yuille , Song Bai

Diffusion Transformers (DiTs) achieve superior image generation quality but suffer from quadratic computational complexity relative to token count. While various token reduction (TR) methods have been proposed to mitigate this cost, they…

Computer Vision and Pattern Recognition · Computer Science 2026-05-22 Hangyeol Lee , Hyojeong Lee , Joo-Young Kim

Is it always necessary to compute tokens from shallow to deep layers in Transformers? The continued success of vanilla Transformers and their variants suggests an undoubted "yes". In this work, however, we attempt to break the depth-ordered…

Computation and Language · Computer Science 2024-07-10 Zhuocheng Gong , Ang Lv , Jian Guan , Junxi Yan , Wei Wu , Huishuai Zhang , Minlie Huang , Dongyan Zhao , Rui Yan

It is widely acknowledged that the performance of Transformer models is logarithmically related to their number of parameters and computational complexity. While approaches like Mixture of Experts (MoE) decouple parameter count from…

Machine Learning · Computer Science 2025-02-07 Zihao Huang , Qiyang Min , Hongzhi Huang , Defa Zhu , Yutao Zeng , Ran Guo , Xun Zhou

Multimodal Large Language Models (MLLMs) have demonstrated substantial value in unified text-image understanding and reasoning, primarily by converting images into sequences of patch-level tokens that align with their architectural…

Computer Vision and Pattern Recognition · Computer Science 2025-11-25 Xinliang Zhang , Lei Zhu , Hangzhou He , Shuang Zeng , Ourui Fu , Jiakui Hu , Zhengjian Yao , Yanye Lu

Tokenization is a fundamental component of language models for code. It involves breaking down the input into units that are later passed to the language model stack to learn high-dimensional representations used in various contexts, from…

Software Engineering · Computer Science 2025-07-22 Mootez Saad , Hao Li , Tushar Sharma , Ahmed E. Hassan

Vision Transformers (ViTs) can learn strong image-level representations while their patch representations become less effective for dense prediction during prolonged training. We revisit this dense degradation phenomenon and argue that it…

Computer Vision and Pattern Recognition · Computer Science 2026-05-25 Linxiang Su

Vision Transformer (ViT) has emerged as a prominent backbone for computer vision. For more efficient ViTs, recent works lessen the quadratic cost of the self-attention layer by pruning or fusing the redundant tokens. However, these works…

Computer Vision and Pattern Recognition · Computer Science 2024-04-02 Sanghyeok Lee , Joonmyung Choi , Hyunwoo J. Kim

Vision Transformers can achieve high accuracy and strong generalization across various contexts, but their practical applicability on real-world robotic systems is limited due to their quadratic attention complexity. Recent works have…

Computer Vision and Pattern Recognition · Computer Science 2026-05-04 Fabio Montello , Ronja Güldenring , Lazaros Nalpantidis

Vision Transformers (ViTs) have achieved state-of-the-art performance across various computer vision tasks, but their high computational cost remains a challenge. Token pruning has been proposed to reduce this cost by selectively removing…

Sound · Computer Science 2025-10-27 Taehan Lee , Hyukjun Lee

We propose Vision Token Turing Machines (ViTTM), an efficient, low-latency, memory-augmented Vision Transformer (ViT). Our approach builds on Neural Turing Machines and Token Turing Machines, which were applied to NLP and sequential visual…

Computer Vision and Pattern Recognition · Computer Science 2025-01-27 Purvish Jajal , Nick John Eliopoulos , Benjamin Shiue-Hal Chou , George K. Thiruvathukal , James C. Davis , Yung-Hsiang Lu

Large Vision-Language Models (LVLMs) have shown impressive performance across multi-modal tasks by encoding images into thousands of tokens. However, the large number of image tokens results in significant computational overhead, and the…

Computer Vision and Pattern Recognition · Computer Science 2025-10-24 Kaiyuan Li , Xiaoyue Chen , Chen Gao , Yong Li , Xinlei Chen