English
Related papers

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

200 papers

We propose TC-AE, a ViT-based architecture for deep compression autoencoders. Existing methods commonly increase the channel number of latent representations to maintain reconstruction quality under high compression ratios. However, this…

Computer Vision and Pattern Recognition · Computer Science 2026-04-09 Teng Li , Ziyuan Huang , Cong Chen , Yangfu Li , Yuanhuiyi Lyu , Dandan Zheng , Chunhua Shen , Jun Zhang

The Rotary Position Embedding (RoPE) mechanism has become a powerful enhancement to the Transformer architecture, which enables models to capture token relationships when encoding positional information. However, the RoPE mechanisms make…

Machine Learning · Computer Science 2026-01-27 Yang Cao , Jiayan Huo , Yingyu Liang , Zhenmei Shi , Zhao Song

Vision Transformers (ViTs) have achieved remarkable success in various computer vision tasks. However, ViTs have a huge computational cost due to their inherent reliance on multi-head self-attention (MHSA), prompting efforts to accelerate…

Computer Vision and Pattern Recognition · Computer Science 2024-12-24 Seungdong Yoa , Seungjun Lee , Hyeseung Cho , Bumsoo Kim , Woohyung Lim

Since its inception, Vision Transformer (ViT) has emerged as a prevalent model in the computer vision domain. Nonetheless, the multi-head self-attention (MHSA) mechanism in ViT is computationally expensive due to its calculation of…

Computer Vision and Pattern Recognition · Computer Science 2023-07-25 Zhe Bian , Zhe Wang , Wenqiang Han , Kangping Wang

KV cache growth is a major bottleneck for long-context inference in large language models. Existing methods are often dominated by binary eviction or representation approximation, which may underutilize tokens that are not critical for…

Machine Learning · Computer Science 2026-05-25 Yuping Lin , Jiayuan Ding , Yue Xing , Pengfei He , Jiliang Tang , Subhabrata Mukherjee

Transformers are central in modern natural language processing and computer vision applications. Despite recent works devoted to reducing the quadratic cost of such models (as a function of the sequence length), dealing with ultra long…

Computation and Language · Computer Science 2023-05-30 Zhanpeng Zeng , Cole Hawkins , Mingyi Hong , Aston Zhang , Nikolaos Pappas , Vikas Singh , Shuai Zheng

The vision transformer splits each image into a sequence of tokens with fixed length and processes the tokens in the same way as words in natural language processing. More tokens normally lead to better performance but considerably…

Computer Vision and Pattern Recognition · Computer Science 2021-12-07 Yichen Zhu , Yuqin Zhu , Jie Du , Yi Wang , Zhicai Ou , Feifei Feng , Jian Tang

Visual localization algorithms have achieved significant improvements in performance thanks to recent advances in camera technology and vision-based techniques. However, there remains one critical caveat: all current approaches that are…

Computer Vision and Pattern Recognition · Computer Science 2019-07-01 Huu Le , Tuan Hoang , Michael Milford

We present AToken, the first unified visual tokenizer that achieves both high-fidelity reconstruction and semantic understanding across images, videos, and 3D assets. Unlike existing tokenizers that specialize in either reconstruction or…

Computer Vision and Pattern Recognition · Computer Science 2025-09-22 Jiasen Lu , Liangchen Song , Mingze Xu , Byeongjoo Ahn , Yanjun Wang , Chen Chen , Afshin Dehghan , Yinfei Yang

In this paper, we introduce the big.LITTLE Vision Transformer, an innovative architecture aimed at achieving efficient visual recognition. This dual-transformer system is composed of two distinct blocks: the big performance block,…

Computer Vision and Pattern Recognition · Computer Science 2024-10-15 He Guo , Yulong Wang , Zixuan Ye , Jifeng Dai , Yuwen Xiong

Recent advancements in vision-language models (VLMs) have expanded their potential for real-world applications, enabling these models to perform complex reasoning on images. In the widely used fully autoregressive transformer-based models…

Computer Vision and Pattern Recognition · Computer Science 2024-10-21 Yuxin Wen , Qingqing Cao , Qichen Fu , Sachin Mehta , Mahyar Najibi

A powerful architecture for universal segmentation relies on transformers that encode multi-scale image features and decode object queries into mask predictions. With efficiency being a high priority for scaling such models, we observed…

Computer Vision and Pattern Recognition · Computer Science 2025-04-01 Abhishek Aich , Yumin Suh , Samuel Schulter , Manmohan Chandraker

Recent large-scale Vision Language Action (VLA) models have shown superior performance in robotic manipulation tasks guided by natural language. However, current VLA models suffer from two drawbacks: (i) generation of massive tokens leading…

Computer Vision and Pattern Recognition · Computer Science 2025-10-06 Juyi Lin , Amir Taherin , Arash Akbari , Arman Akbari , Lei Lu , Guangyu Chen , Taskin Padir , Xiaomeng Yang , Weiwei Chen , Yiqian Li , Xue Lin , David Kaeli , Pu Zhao , Yanzhi Wang

Many images and videos are primarily processed by computer vision algorithms, involving only occasional human inspection. When this content requires compression before processing, e.g., in distributed applications, coding methods must…

Image and Video Processing · Electrical Eng. & Systems 2025-08-27 Samuel Fernández-Menduiña , Eduardo Pavez , Antonio Ortega

Tomography has had an important impact on the physical, biological, and medical sciences. To date, most tomographic applications have been focused on 3D scalar reconstructions. However, in some crucial applications, vector tomography is…

Medical Physics · Physics 2023-10-20 Minh Pham , Xingyuan Lu , Arjun Rana , Stanley Osher , Jianwei Miao

Rotary Position Embedding (RoPE) has become a core component of modern Transformer architectures across language, vision, and 3D domains. However, existing implementations rely on vector-level split and merge operations that introduce…

Machine Learning · Computer Science 2026-04-14 Chen Minqi , Zhongqi Yue , Shihao Zhang , Yun Xu , Peng Wu , kaixiang Xu , Zeyi Huang , Hanwang Zhang

Running AI models on smart edge devices can unlock versatile user experiences, but presents challenges due to limited compute and the need to handle multiple tasks simultaneously. This requires a vision encoder with small size but powerful…

Computer Vision and Pattern Recognition · Computer Science 2026-04-01 Chenchen Zhu , Saksham Suri , Cijo Jose , Maxime Oquab , Marc Szafraniec , Wei Wen , Yunyang Xiong , Patrick Labatut , Piotr Bojanowski , Raghuraman Krishnamoorthi , Vikas Chandra

Our objective is language-based search of large-scale image and video datasets. For this task, the approach that consists of independently mapping text and vision to a joint embedding space, a.k.a. dual encoders, is attractive as retrieval…

Computer Vision and Pattern Recognition · Computer Science 2021-03-31 Antoine Miech , Jean-Baptiste Alayrac , Ivan Laptev , Josef Sivic , Andrew Zisserman

We present a novel approach to enhance the capabilities of VQ-VAE models through the integration of a Residual Encoder and a Residual Pixel Attention layer, named Attentive Residual Encoder (AREN). The objective of our research is to…

Computer Vision and Pattern Recognition · Computer Science 2024-02-12 Angello Hoyos , Mariano Rivera

Vision Transformer (ViT) based autoencoders often underutilize the global Class token and employ static attention mechanisms, limiting both generative control and optimization efficiency. This paper introduces ViTCAE, a framework that…

Machine Learning · Computer Science 2025-09-23 Vahid Jebraeeli , Hamid Krim , Derya Cansever