English
Related papers

Related papers: TokenFormer: Rethinking Transformer Scaling with T…

200 papers

Transformers have achieved great success in effectively processing sequential data such as text. Their architecture consisting of several attention and feedforward blocks can model relations between elements of a sequence in parallel…

Machine Learning · Computer Science 2025-02-20 Jaemu Heo , Eldor Fozilov , Hyunmin Song , Taehwan Kim

Scaling Transformers typically necessitates training larger models from scratch, as standard architectures struggle to expand without discarding learned representations. We identify the primary bottleneck in the attention mechanism's linear…

Machine Learning · Computer Science 2026-04-22 Weijie Zhao , Mingquan Liu , Bolun Wang , Simo Wu , Nuobei Xie , Rui-Jie Zhu , Peng Zhou

The Transformer architecture has become a cornerstone of modern artificial intelligence, but its core self-attention mechanism suffers from a complexity bottleneck that scales quadratically with sequence length, severely limiting its…

Machine Learning · Computer Science 2025-08-29 Zhongpan Tang

Tokenization is a fundamental component of large language models (LLMs), yet its influence on model scaling and performance is not fully explored. In this paper, we introduce Over-Tokenized Transformers, a novel framework that decouples…

Computation and Language · Computer Science 2025-05-26 Hongzhi Huang , Defa Zhu , Banggu Wu , Yutao Zeng , Ya Wang , Qiyang Min , Xun Zhou

State-of-the-art results in large language models (LLMs) often rely on scale, which becomes computationally expensive. This has sparked a research agenda to reduce these models' parameter counts and computational costs without significantly…

Computation and Language · Computer Science 2024-11-07 Xiuying Wei , Skander Moalla , Razvan Pascanu , Caglar Gulcehre

Learning representations on large-sized graphs is a long-standing challenge due to the inter-dependence nature involved in massive data points. Transformers, as an emerging class of foundation encoders for graph-structured data, have shown…

Machine Learning · Computer Science 2024-08-19 Qitian Wu , Wentao Zhao , Chenxiao Yang , Hengrui Zhang , Fan Nie , Haitian Jiang , Yatao Bian , Junchi Yan

Transformers have emerged as the state-of-the-art architecture in medical image registration, outperforming convolutional neural networks (CNNs) by addressing their limited receptive fields and overcoming gradient instability in deeper…

Computer Vision and Pattern Recognition · Computer Science 2024-12-03 Abu Zahid Bin Aziz , Mokshagna Sai Teja Karanam , Tushar Kataria , Shireen Y. Elhabian

To analyze the scaling potential of deep tabular representation learning models, we introduce a novel Transformer-based architecture specifically tailored to tabular data and cross-table representation learning by utilizing table-specific…

Machine Learning · Computer Science 2023-10-02 Maximilian Schambach , Dominique Paul , Johannes S. Otterbach

Real-world time series data are inherently multivariate, often exhibiting complex inter-channel dependencies. Each channel is typically sampled at its own period and is prone to missing values due to various practical and operational…

Machine Learning · Computer Science 2026-03-11 Jinkwan Jang , Hyungjin Park , Jinmyeong Choi , Taesup Kim

Transformer is a transformative framework that models sequential data and has achieved remarkable performance on a wide range of tasks, but with high computational and energy cost. To improve its efficiency, a popular choice is to compress…

Computer Vision and Pattern Recognition · Computer Science 2023-03-21 Jing Liu , Zizheng Pan , Haoyu He , Jianfei Cai , Bohan Zhuang

We present Token-UNet, adopting the TokenLearner and TokenFuser modules to encase Transformers into UNets. While Transformers have enabled global interactions among input elements in medical imaging, current computational challenges hinder…

Computer Vision and Pattern Recognition · Computer Science 2026-02-24 Louis Fabrice Tshimanga , Andrea Zanola , Federico Del Pup , Manfredo Atzori

Sequential user modeling, a critical task in personalized recommender systems, focuses on predicting the next item a user would prefer, requiring a deep understanding of user behavior sequences. Despite the remarkable success of…

Artificial Intelligence · Computer Science 2023-10-10 Hao Wang , Jianxun Lian , Mingqi Wu , Haoxuan Li , Jiajun Fan , Wanyue Xu , Chaozhuo Li , Xing Xie

Linearization has emerged as a strategy for developing efficient language models (LMs). Starting from an existing Transformer-based LM, linearization replaces the attention component with computationally efficient subquadratic \textit{token…

Computation and Language · Computer Science 2026-02-02 Patrick Haller , Jonas Golde , Alan Akbik

In Transformer architectures, tokens\textemdash discrete units derived from raw data\textemdash are formed by segmenting inputs into fixed-length chunks. Each token is then mapped to an embedding, enabling parallel attention computations…

Machine Learning · Computer Science 2026-01-14 Zhenglun Kong , Yize Li , Fanhu Zeng , Lei Xin , Shvat Messica , Xue Lin , Pu Zhao , Manolis Kellis , Hao Tang , Marinka Zitnik

Recently, a variety of vision transformers have been developed as their capability of modeling long-range dependency. In current transformer-based backbones for medical image segmentation, convolutional layers were replaced with pure…

Computer Vision and Pattern Recognition · Computer Science 2022-08-01 Huimin Huang , Shiao Xie1 , Lanfen Lin , Yutaro Iwamoto , Xianhua Han , Yen-Wei Chen , Ruofeng Tong

As industrial recommender systems enter a scaling-driven regime, Transformer architectures have become increasingly attractive for scaling models towards larger capacity and longer sequence. However, existing Transformer-based…

Information Retrieval · Computer Science 2026-02-17 Xu Huang , Hao Zhang , Zhifang Fan , Yunwen Huang , Zhuoxing Wei , Zheng Chai , Jinan Ni , Yuchao Zheng , Qiwei Chen

Transformers process tokens in parallel but are temporally shallow: at position $t$, each layer attends to key-value pairs computed based on the previous layer, yielding a depth capped by the number of layers. Recurrent models offer…

Machine Learning · Computer Science 2026-04-24 Costin-Andrei Oncescu , Depen Morwani , Samy Jelassi , Alexandru Meterez , Mujin Kwun , Sham Kakade

The architecture of transformers, which recently witness booming applications in vision tasks, has pivoted against the widespread convolutional paradigm. Relying on the tokenization process that splits inputs into multiple tokens,…

Computer Vision and Pattern Recognition · Computer Science 2022-12-22 Shengju Qian , Yi Zhu , Wenbo Li , Mu Li , Jiaya Jia

Despite the remarkable success of transformer architectures in natural language processing, their scalability limitations remain poorly understood through systematic empirical analysis. This paper presents the first comprehensive…

Machine Learning · Computer Science 2026-05-18 Mahdi Naser Moghadasi , Faezeh Ghaderi

The quadratic complexity of standard self-attention severely limits the application of Transformer-based models to long-context tasks. While efficient Transformer variants exist, they often require architectural changes and costly…

Computation and Language · Computer Science 2025-11-14 Jiangshu Du , Wenpeng Yin , Philip Yu
‹ Prev 1 2 3 10 Next ›