English
Related papers

Related papers: Active Token Mixer

200 papers

Model merging has emerged as a cost-efficient approximation to multitask learning. Among merging strategies, task arithmetic is notable for its simplicity and effectiveness. In this work, we provide a theoretical motivation for task vectors…

Large Language Models (LLMs) have achieved impressive performance across diverse tasks but continue to struggle with learning transitive relations, a cornerstone for complex planning. To address this issue, we investigate the Multi-Token…

Artificial Intelligence · Computer Science 2025-09-30 Qimin Zhong , Hao Liao , Siwei Wang , Mingyang Zhou , Xiaoqun Wu , Rui Mao , Wei Chen

Token compression is essential for reducing the computational and memory requirements of transformer models, enabling their deployment in resource-constrained environments. In this work, we propose an efficient and hardware-compatible token…

Computer Vision and Pattern Recognition · Computer Science 2025-04-01 Junzhu Mao , Yang Shen , Jinyang Guo , Yazhou Yao , Xiansheng Hua

This paper presents an adaptive convolutional neural network (CNN) architecture that can automate diverse topology optimization (TO) problems having different underlying physics. The architecture uses the encoder-decoder networks with dense…

Computational Engineering, Finance, and Science · Computer Science 2025-09-10 Khaish Singh Chadha , Prabhat Kumar

Transformers are widely used in computer vision areas and have achieved remarkable success. Most state-of-the-art approaches split images into regular grids and represent each grid region with a vision token. However, fixed token…

Computer Vision and Pattern Recognition · Computer Science 2024-07-17 Wang Zeng , Sheng Jin , Lumin Xu , Wentao Liu , Chen Qian , Wanli Ouyang , Ping Luo , Xiaogang Wang

Despite their simpler information fusion designs compared with Vision Transformers and Convolutional Neural Networks, Vision MLP architectures have demonstrated strong performance and high data efficiency in recent research. However,…

Computer Vision and Pattern Recognition · Computer Science 2024-10-28 Jonathan Cui , David A. Araujo , Suman Saha , Md. Faisal Kabir

While Large Vision-Language Models (LVLMs) demonstrate exceptional multi-modal capabilities, the quadratic computational cost of processing high-resolution visual tokens remains a critical bottleneck. Though recent token reduction…

Computer Vision and Pattern Recognition · Computer Science 2026-03-19 Surendra Pathak , Bo Han

In recent years, how to strike a good trade-off between accuracy and inference speed has become the core issue for real-time semantic segmentation applications, which plays a vital role in real-world scenarios such as autonomous driving…

Computer Vision and Pattern Recognition · Computer Science 2021-07-19 Guangwei Gao , Guoan Xu , Yi Yu , Jin Xie , Jian Yang , Dong Yue

Vision Transformers (ViTs) have achieved strong performance in visual recognition, yet their deployment in resource-constrained industrial environments remains limited. Some main challenges are their high computational cost, memory…

Computer Vision and Pattern Recognition · Computer Science 2026-05-05 Phat Nguyen , Xue Geng , Kaixin Xu , Wang Zhe , Xulei Yang , Ngai-Man Cheung

State-of-the-art speech-to-text models typically employ Transformer-based encoders that model token dependencies via self-attention mechanisms. However, the quadratic complexity of self-attention in both memory and computation imposes…

Computation and Language · Computer Science 2026-03-03 Eva Feillet , Ryan Whetten , David Picard , Alexandre Allauzen

Transformer-based models have achieved state-of-the-art results in many natural language processing tasks. The self-attention architecture allows transformer to combine information from all elements of a sequence into context-aware…

Computation and Language · Computer Science 2021-02-17 Mikhail S. Burtsev , Yuri Kuratov , Anton Peganov , Grigory V. Sapunov

Transformers exhibit great advantages in handling computer vision tasks. They model image classification tasks by utilizing a multi-head attention mechanism to process a series of patches consisting of split images. However, for complex…

Computer Vision and Pattern Recognition · Computer Science 2022-03-22 Haichao Zhang , Kuangrong Hao , Witold Pedrycz , Lei Gao , Xuesong Tang , Bing Wei

This paper presents MOAT, a family of neural networks that build on top of MObile convolution (i.e., inverted residual blocks) and ATtention. Unlike the current works that stack separate mobile convolution and transformer blocks, we…

Computer Vision and Pattern Recognition · Computer Science 2023-02-01 Chenglin Yang , Siyuan Qiao , Qihang Yu , Xiaoding Yuan , Yukun Zhu , Alan Yuille , Hartwig Adam , Liang-Chieh Chen

Recently, transformer networks have outperformed traditional deep neural networks in natural language processing and show a large potential in many computer vision tasks compared to convolutional backbones. In the original transformer,…

Computer Vision and Pattern Recognition · Computer Science 2023-03-03 Chen-Chou Lo , Patrick Vandewalle

In this paper, we present a novel deep fusion architecture for audio classification tasks. The multi-channel model presented is formed using deep convolution layers where different acoustic features are passed through each channel. To…

Sound · Computer Science 2018-11-05 Gaurav Bhatt , Akshita Gupta , Aditya Arora , Balasubramanian Raman

Token communications (TokCom) is an emerging generative semantic communication concept that reduces transmission rates by using context and multimodal large language model (MLLM)-based token processing, with tokens serving as universal…

Information Theory · Computer Science 2025-09-11 Li Qiao , Mahdi Boloursaz Mashhadi , Zhen Gao , Robert Schober , Deniz Gündüz

While the Self-Attention mechanism in the Transformer model has proven to be effective in many domains, we observe that it is less effective in more diverse settings (e.g. multimodality) due to the varying granularity of each token and the…

Computer Vision and Pattern Recognition · Computer Science 2024-06-06 Wayner Barrios , SouYoung Jin

We propose integrally pre-trained transformer pyramid network (iTPN), towards jointly optimizing the network backbone and the neck, so that transfer gap between representation models and downstream tasks is minimal. iTPN is born with two…

Computer Vision and Pattern Recognition · Computer Science 2024-01-08 Yunjie Tian , Lingxi Xie , Jihao Qiu , Jianbin Jiao , Yaowei Wang , Qi Tian , Qixiang Ye

Recent progress in spatial reasoning with Multimodal Large Language Models (MLLMs) increasingly leverages geometric priors from 3D encoders. However, most existing integration strategies remain passive: geometry is exposed as a global…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Haoyuan Li , Qihang Cao , Tao Tang , Kun Xiang , Zihan Guo , Jianhua Han , JiaWang Bian , Hang Xu , Xiaodan Liang

Very recently, a variety of vision transformer architectures for dense prediction tasks have been proposed and they show that the design of spatial attention is critical to their success in these tasks. In this work, we revisit the design…

Computer Vision and Pattern Recognition · Computer Science 2021-10-01 Xiangxiang Chu , Zhi Tian , Yuqing Wang , Bo Zhang , Haibing Ren , Xiaolin Wei , Huaxia Xia , Chunhua Shen