English
Related papers

Related papers: What Matters in Transformers? Not All Attention is…

200 papers

Transformer-based models have demonstrated remarkable in-context learning capabilities, prompting extensive research into its underlying mechanisms. Recent studies have suggested that Transformers can implement first-order optimization…

Machine Learning · Computer Science 2024-03-06 Angeliki Giannou , Liu Yang , Tianhao Wang , Dimitris Papailiopoulos , Jason D. Lee

Transformers have sprung up in the field of computer vision. In this work, we explore whether the core self-attention module in Transformer is the key to achieving excellent performance in image recognition. To this end, we build an…

Computer Vision and Pattern Recognition · Computer Science 2022-05-31 Chuanxin Tang , Yucheng Zhao , Guangting Wang , Chong Luo , Wenxuan Xie , Wenjun Zeng

Large Language Models (LLMs) are known for their performance, but we uncover a significant structural inefficiency: a phenomenon we term attention collapse. In many pre-trained decoder-style LLMs, the attention matrices in deeper layers…

Computation and Language · Computer Science 2026-02-17 Sunny Sanyal , Ravid Shwartz-Ziv , Alexandros G. Dimakis , Sujay Sanghavi

Transformer has become ubiquitous in natural language processing (e.g., machine translation, question answering); however, it requires enormous amount of computations to achieve high performance, which makes it not suitable for mobile…

Computation and Language · Computer Science 2020-04-27 Zhanghao Wu , Zhijian Liu , Ji Lin , Yujun Lin , Song Han

Large Language Models are growing in size, and we expect them to continue to do so, as larger models train quicker. However, this increase in size will severely impact inference costs. Therefore model compression is important, to retain the…

Machine Learning · Computer Science 2024-04-10 Georgy Tyukin

Since its inception in "Attention Is All You Need", transformer architecture has led to revolutionary advancements in NLP. The attention layer within the transformer admits a sequence of input tokens $X$ and makes them interact through…

Machine Learning · Computer Science 2024-02-23 Davoud Ataee Tarzanagh , Yingcong Li , Christos Thrampoulidis , Samet Oymak

Transformer layers, which use an alternating pattern of multi-head attention and multi-layer perceptron (MLP) layers, provide an effective tool for a variety of machine learning problems. As the transformer layers use residual connections…

Machine Learning · Computer Science 2022-12-13 Yaofeng Desmond Zhong , Tongtao Zhang , Amit Chakraborty , Biswadip Dey

Multimodal Transformers serve as the backbone for state-of-the-art vision-language models, yet their quadratic attention complexity remains a critical barrier to scalability. In this work, we investigate the viability of Linear Attention…

Computer Vision and Pattern Recognition · Computer Science 2026-04-14 Armin Gerami , Seyedehanita Madani , Ramani Duraiswami

Transformer architectures deliver state-of-the-art accuracy via dense full-attention, but their quadratic time and memory complexity with respect to sequence length limits practical deployment. Linear attention mechanisms offer linear or…

Machine Learning · Computer Science 2026-01-21 Xiaojie Xia , Huigang Zhang , Chaoliang Zhong , Jun Sun , Yusuke Oishi

Computational workloads composing traditional transformer models are starkly bifurcated. Multi-Head Attention (MHA) and Grouped-Query Attention are memory-bound due to low arithmetic intensity, while FeedForward Networks are compute-bound.…

Transformers are the current architecture of choice for NLP, but their attention layers do not scale well to long contexts. Recent works propose to replace attention with linear recurrent layers -- this is the case for state space models,…

Computation and Language · Computer Science 2024-07-09 Hugo Pitorro , Pavlo Vasylenko , Marcos Treviso , André F. T. Martins

Large language models (LLMs) have proven to be highly effective across various natural language processing tasks. However, their large number of parameters poses significant challenges for practical deployment. Pruning, a technique aimed at…

Computation and Language · Computer Science 2024-12-16 Jiwon Song , Kyungseok Oh , Taesu Kim , Hyungjun Kim , Yulhwa Kim , Jae-Joon Kim

With the increasing demand for practical applications of Large Language Models (LLMs), many attention-efficient models have been developed to balance performance and computational cost. However, the adversarial robustness of these models…

Computation and Language · Computer Science 2024-09-17 Xiaojing Fan , Chunliang Tao

Recent large language models (LLMs) have revealed strong abilities to understand natural language. Since most of them share the same basic structure, i.e. the transformer block, possible contributors to their success in the training process…

Computation and Language · Computer Science 2023-10-31 Changjiang Gao , Shujian Huang , Jixing Li , Jiajun Chen

The transformer architecture is widely used in machine learning models and consists of two alternating sublayers: attention heads and MLPs. We prove that an MLP neuron can be implemented by a masked attention head with internal dimension 1…

Machine Learning · Computer Science 2023-09-18 Robert Huben , Valerie Morris

Large language models (LLMs) are known for their exceptional performance in natural language processing, making them highly effective in many human life-related or even job-related tasks. The attention mechanism in the Transformer…

Computation and Language · Computer Science 2023-04-27 Shuai Li , Zhao Song , Yu Xia , Tong Yu , Tianyi Zhou

Linear RNN architectures, like Mamba, can be competitive with Transformer models in language modeling while having advantageous deployment characteristics. Given the focus on training large-scale Transformer models, we consider the…

Machine Learning · Computer Science 2025-06-30 Junxiong Wang , Daniele Paliotta , Avner May , Alexander M. Rush , Tri Dao

Decoder-only transformer networks have become incredibly popular for language modeling tasks. State-of-the-art models can have over a hundred transformer blocks, containing billions of trainable parameters, and are trained on trillions of…

Computation and Language · Computer Science 2025-05-13 Isaac Gerber

Transformers have become foundational architectures for both natural language and computer vision tasks. However, the high computational cost makes it quite challenging to deploy on resource-constraint devices. This paper investigates the…

Computer Vision and Pattern Recognition · Computer Science 2024-06-18 Jialong Guo , Xinghao Chen , Yehui Tang , Yunhe Wang

State-of-the-art results on neural machine translation often use attentional sequence-to-sequence models with some form of convolution or recursion. Vaswani et al. (2017) propose a new architecture that avoids recurrence and convolution…

Artificial Intelligence · Computer Science 2017-11-08 Karim Ahmed , Nitish Shirish Keskar , Richard Socher