English
Related papers

Related papers: Synthesizer: Rethinking Self-Attention in Transfor…

200 papers

Transformers have proven highly effective across modalities, but standard softmax attention scales quadratically with sequence length, limiting long context modeling. Linear attention mitigates this by approximating attention with kernel…

Machine Learning · Computer Science 2026-02-10 Ashkan Shahbazi , Chayne Thrash , Yikun Bai , Keaton Hamm , Navid NaderiAlizadeh , Soheil Kolouri

The dominant sequence transduction models are based on complex recurrent or convolutional neural networks in an encoder-decoder configuration. The best performing models also connect the encoder and decoder through an attention mechanism.…

Computation and Language · Computer Science 2023-08-03 Ashish Vaswani , Noam Shazeer , Niki Parmar , Jakob Uszkoreit , Llion Jones , Aidan N. Gomez , Lukasz Kaiser , Illia Polosukhin

In this paper we delve deep in the Transformer architecture by investigating two of its core components: self-attention and contextual embeddings. In particular, we study the identifiability of attention weights and token embeddings, and…

Computation and Language · Computer Science 2020-02-10 Gino Brunner , Yang Liu , Damián Pascual , Oliver Richter , Massimiliano Ciaramita , Roger Wattenhofer

Transformers provide a class of expressive architectures that are extremely effective for sequence modeling. However, the key limitation of transformers is their quadratic memory and time complexity $\mathcal{O}(L^2)$ with respect to the…

Machine Learning · Computer Science 2021-10-29 Hongyu Ren , Hanjun Dai , Zihang Dai , Mengjiao Yang , Jure Leskovec , Dale Schuurmans , Bo Dai

Transformer architecture has become ubiquitous in the natural language processing field. To interpret the Transformer-based models, their attention patterns have been extensively analyzed. However, the Transformer architecture is not only…

Computation and Language · Computer Science 2021-09-16 Goro Kobayashi , Tatsuki Kuribayashi , Sho Yokoi , Kentaro Inui

Recent works have revealed that Transformers are implicitly learning the syntactic information in its lower layers from data, albeit is highly dependent on the quality and scale of the training data. However, learning syntactic information…

Computation and Language · Computer Science 2022-10-24 Shengyuan Hou , Jushi Kai , Haotian Xue , Bingyu Zhu , Bo Yuan , Longtao Huang , Xinbing Wang , Zhouhan Lin

Recent work has shown that training loss scales as a power law with both model size and the number of tokens, and that achieving compute-optimal models requires scaling model size and token count together. However, these scaling laws assume…

Machine Learning · Computer Science 2025-07-04 Aurko Roy , Timothy Chou , Sai Surya Duvvuri , Sijia Chen , Jiecao Yu , Xiaodong Wang , Manzil Zaheer , Rohan Anil

Diffusion Transformers (DiT) have become a leading architecture in image generation. However, the quadratic complexity of attention mechanisms, which are responsible for modeling token-wise relationships, results in significant latency when…

Computer Vision and Pattern Recognition · Computer Science 2024-12-23 Songhua Liu , Zhenxiong Tan , Xinchao Wang

The self-attention mechanism, at the heart of the Transformer model, is able to effectively model pairwise interactions between tokens. However, numerous recent works have shown that it is unable to perform basic tasks involving detecting…

Machine Learning · Computer Science 2026-02-03 Sayak Chakrabarti , Toniann Pitassi , Josh Alman

In this paper, we propose a simple and effective technique to allow for efficient self-supervised learning with bi-directional Transformers. Our approach is motivated by recent studies demonstrating that self-attention patterns in trained…

Computation and Language · Computer Science 2020-10-07 Ameet Deshpande , Karthik Narasimhan

Transformer-based models have achieved dominant performance in numerous NLP tasks. Despite their remarkable successes, pre-trained transformers such as BERT suffer from a computationally expensive self-attention mechanism that interacts…

Computation and Language · Computer Science 2024-06-04 Jungmin Yun , Mihyeon Kim , Youngbin Kim

Transformers have demonstrated remarkable performance across diverse domains. The key component of Transformers is self-attention, which learns the relationship between any two tokens in the input sequence. Recent studies have revealed that…

Machine Learning · Computer Science 2025-05-14 Hyowon Wi , Jeongwhan Choi , Noseong Park

Transformers are widely used for their ability to capture data relations in sequence processing, with great success for a wide range of static tasks. However, the computational and memory footprint of their main component, i.e., the Scaled…

Computer Vision and Pattern Recognition · Computer Science 2025-07-29 Ginés Carreto Picón , Illia Oleksiienko , Lukas Hedegaard , Arian Bakhtiarnia , Alexandros Iosifidis

The powerful modeling capabilities of all-attention-based transformer architectures often cause overfitting and - for natural language processing tasks - lead to an implicitly learned internal language model in the autoregressive…

Machine Learning · Computer Science 2022-09-21 Timo Lohrenz , Björn Möller , Zhengyang Li , Tim Fingscheidt

Vision Transformers has demonstrated competitive performance on computer vision tasks benefiting from their ability to capture long-range dependencies with multi-head self-attention modules and multi-layer perceptron. However, calculating…

Computer Vision and Pattern Recognition · Computer Science 2022-10-25 Xiangyu Chen , Qinghao Hu , Kaidong Li , Cuncong Zhong , Guanghui Wang

Standard attention mechanisms in transformers employ static token representations that remain unchanged across all pair-wise computations in each layer. This limits their representational alignment with the potentially diverse relational…

Machine Learning · Computer Science 2026-05-26 Hunjae Lee , Corey Clark

Transformers have been proven a successful model for a variety of tasks in sequence modeling. However, computing the attention matrix, which is their key component, has quadratic complexity with respect to the sequence length, thus making…

Machine Learning · Computer Science 2020-10-01 Apoorv Vyas , Angelos Katharopoulos , François Fleuret

In the Transformer model, "self-attention" combines information from attended embeddings into the representation of the focal embedding in the next layer. Thus, across layers of the Transformer, information originating from different tokens…

Machine Learning · Computer Science 2020-06-02 Samira Abnar , Willem Zuidema

Many empirical studies have provided evidence for the emergence of algorithmic mechanisms (abilities) in the learning of language models, that lead to qualitative improvements of the model capabilities. Yet, a theoretical characterization…

Machine Learning · Computer Science 2025-02-10 Hugo Cui , Freya Behrens , Florent Krzakala , Lenka Zdeborová

Despite the significant progress made by transformer models in machine reading comprehension tasks, they still fall short in handling complex reasoning tasks due to the absence of explicit knowledge in the input sequence. To address this…

Computation and Language · Computer Science 2024-01-17 Shima Foolad , Kourosh Kiani