English
Related papers

Related papers: TORE: Token Recycling in Vision Transformers for E…

200 papers

We propose Token Turing Machines (TTM), a sequential, autoregressive Transformer model with memory for real-world sequential visual understanding. Our model is inspired by the seminal Neural Turing Machine, and has an external memory…

Variational autoencoders are among the most popular methods for distilling low-dimensional structure from high-dimensional data, making them increasingly valuable as tools for data exploration and scientific discovery. However, unlike…

Machine Learning · Computer Science 2022-01-17 Miles Martinez , John Pearson

Recently, reducing redundant visual tokens in vision-language models (VLMs) to accelerate VLM inference has emerged as a hot topic. However, most existing methods rely on heuristics constructed based on inter-visual-token similarity or…

Computer Vision and Pattern Recognition · Computer Science 2026-05-15 Haokui Zhang , Congyang Ou , Dawei Yan , Peng Wang , Qingsen Yan , Yu Zhang , Ying Li , Rong Xiao

Transformers dominate video recognition. They split videos into tokens, and processing them has expensive superlinear computational cost. Yet videos are filled with redundancy, so we can question the need for this expense. We introduce…

Computer Vision and Pattern Recognition · Computer Science 2026-05-11 Ali Salamatian , Anthony Fuller , Pritam Sarkar , James R. Green , Leonid Sigal , Evan Shelhamer

Object-centric representations form the basis of human perception, and enable us to reason about the world and to systematically generalize to new settings. Currently, most works on unsupervised object discovery focus on slot-based…

Machine Learning · Computer Science 2022-11-21 Sindy Löwe , Phillip Lippe , Maja Rudolph , Max Welling

Recent end-to-end automatic speech recognition (ASR) systems often utilize a Transformer-based acoustic encoder that generates embedding at a high frame rate. However, this design is inefficient, particularly for long speech signals due to…

Computation and Language · Computer Science 2023-06-29 Yuang Li , Yu Wu , Jinyu Li , Shujie Liu

In this paper, we propose a novel token selective attention approach, ToSA, which can identify tokens that need to be attended as well as those that can skip a transformer layer. More specifically, a token selector parses the current…

Computer Vision and Pattern Recognition · Computer Science 2024-06-14 Manish Kumar Singh , Rajeev Yasarla , Hong Cai , Mingu Lee , Fatih Porikli

Context. In order to overcome the radial velocity (RV) precision barrier imposed by stellar variability, there has been a surge of software aimed at simulating and modeling these activity patterns. Aims. We present Analyzing Radial Velocity…

Instrumentation and Methods for Astrophysics · Physics 2025-07-28 K. Al Moulla

Transformers have recently emerged as a powerful tool for learning visual representations. In this paper, we identify and characterize artifacts in feature maps of both supervised and self-supervised ViT networks. The artifacts correspond…

Computer Vision and Pattern Recognition · Computer Science 2024-04-15 Timothée Darcet , Maxime Oquab , Julien Mairal , Piotr Bojanowski

Visual geometry transformers have become powerful architectures for multi-view 3D reconstruction, enabling joint prediction of multiple 3D attributes in a feed-forward manner. However, their computational cost grows quadratically with the…

Computer Vision and Pattern Recognition · Computer Science 2026-05-25 Shuhong Zheng , Michael Oechsle , Erik Sandström , Marie-Julie Rakotosaona , Federico Tombari , Igor Gilitschenski

Vision transformer has achieved impressive performance for many vision tasks. However, it may suffer from high redundancy in capturing local features for shallow layers. Local self-attention or early-stage convolutions are thus utilized,…

Computer Vision and Pattern Recognition · Computer Science 2024-01-26 Huaibo Huang , Xiaoqiang Zhou , Jie Cao , Ran He , Tieniu Tan

Vision Transformers (ViTs) enable strong multi-view 3D detection but are limited by high inference latency from dense token and query processing across multiple views and large 3D regions. Existing sparsity methods, designed mainly for 2D…

Computer Vision and Pattern Recognition · Computer Science 2026-05-15 Sandro Papais , Lezhou Feng , Charles Cossette , Lingting Ge

Visual recognition has been dominated by convolutional neural networks (CNNs) for years. Though recently the prevailing vision transformers (ViTs) have shown great potential of self-attention based models in ImageNet classification, their…

Computer Vision and Pattern Recognition · Computer Science 2021-06-29 Li Yuan , Qibin Hou , Zihang Jiang , Jiashi Feng , Shuicheng Yan

Vision-Language Models suffer severe KV cache pressure at inference, as a single image often encodes into thousands of tokens. Most existing methods exploit token sparsity through token pruning, but permanently discarding visual content…

Computer Vision and Pattern Recognition · Computer Science 2026-05-20 Beomseok Kang , Dongwon Jo , Jiwon Song , Donghwee Son , Jae-Joon Kim

Transformers rely on positional encoding to compensate for the inherent permutation invariance of self-attention. Traditional approaches use absolute sinusoidal embeddings or learned positional vectors, while more recent methods emphasize…

Machine Learning · Computer Science 2025-11-18 Chase van de Geijn , Ayush Paliwal , Timo Lüddecke , Alexander S. Ecker

In recent studies, it could be shown that the energy demand of Versatile Video Coding (VVC) decoders can be twice as high as comparable High Efficiency Video Coding (HEVC) decoders. A significant part of this increase in complexity is…

Image and Video Processing · Electrical Eng. & Systems 2024-02-16 Matthias Kränzler , Christian Herglotz , André Kaup

Mixture of Vision Encoders (MoVE) has emerged as a powerful approach to enhance the fine-grained visual understanding of multimodal large language models (MLLMs), improving their ability to handle tasks such as complex optical character…

Computer Vision and Pattern Recognition · Computer Science 2026-03-09 Mozhgan Nasr Azadani , James Riddell , Sean Sedwards , Krzysztof Czarnecki

Vision-language models (VLMs) benefit from multiple vision encoders, but naively stacking them yields diminishing returns while multiplying inference costs. We propose SCOPE, a Mixture-of-Encoders (MoEnc) framework that dynamically selects…

Computer Vision and Pattern Recognition · Computer Science 2025-10-20 Tianyu Zhang , Suyuchen Wang , Chao Wang , Juan Rodriguez , Ahmed Masry , Xiangru Jian , Yoshua Bengio , Perouz Taslakian

Inspired by the remarkable success of autoregressive models in language modeling, this paradigm has been widely adopted in visual generation. However, the sequential token-by-token decoding mechanism inherent in traditional autoregressive…

Computer Vision and Pattern Recognition · Computer Science 2026-01-01 Siyang Wang , Hanting Li , Wei Li , Jie Hu , Xinghao Chen , Feng Zhao

Vision Transformers (ViTs) have emerged as powerful models in the field of computer vision, delivering superior performance across various vision tasks. However, the high computational complexity poses a significant barrier to their…

Computer Vision and Pattern Recognition · Computer Science 2024-02-06 Xinjian Wu , Fanhu Zeng , Xiudong Wang , Xinghao Chen
‹ Prev 1 3 4 5 6 7 10 Next ›