English
Related papers

Related papers: Energy-Gated Attention and Wavelet Positional Enco…

200 papers

Transformer attention architectures, similar to those developed for natural language processing, have recently proved efficient also in vision, either in conjunction with or as a replacement for convolutional layers. Typically, visual…

Computer Vision and Pattern Recognition · Computer Science 2021-07-01 Rufin VanRullen , Andrea Alamia

The computational burden of attention in long-context language models has motivated two largely independent lines of work: sparse attention mechanisms that reduce complexity by attending to selected tokens, and gated attention variants that…

Artificial Intelligence · Computer Science 2026-01-23 Alfred Shen , Aaron Shen

The self-attention module is a key component of Transformer-based models, wherein each token pays attention to every other token. Recent studies have shown that these heads exhibit syntactic, semantic, or local behaviour. Some studies have…

Computation and Language · Computer Science 2020-08-14 Madhura Pande , Aakriti Budhraja , Preksha Nema , Pratyush Kumar , Mitesh M. Khapra

Transformer-based models have demonstrated considerable potential for source code modeling tasks in software engineering. However, they are limited by their dependence solely on automatic self-attention weight learning mechanisms. Previous…

Software Engineering · Computer Science 2024-02-27 Jiri Gesi , Iftekhar Ahmed

In this work, we investigate the positional encoding methods used in language pre-training (e.g., BERT) and identify several problems in the existing formulations. First, we show that in the absolute positional encoding, the addition…

Computation and Language · Computer Science 2021-03-16 Guolin Ke , Di He , Tie-Yan Liu

In the realm of large-scale language models, a significant challenge arises when extrapolating sequences beyond the maximum allowable length. This is because the model's position embedding mechanisms are limited to positions encountered…

Computation and Language · Computer Science 2025-02-05 Yui Oka , Taku Hasegawa , Kyosuke Nishida , Kuniko Saito

We use a mean-field-based transformer model to theoretically investigate how auxiliary variables, such as positional encoding, prevent mode collapse of self-attention mechanisms. The use of mean-field transformers to analyze the properties…

Machine Learning · Computer Science 2026-05-29 Masaaki Imaizumi , Masanori Koyama , Noboru Isobe , Kohei Hayashi

We explain why directly changing the prior can be a surprisingly ineffective mechanism for incorporating inductive biases into VAEs, and introduce a simple and effective alternative approach: Intermediary Latent Space VAEs(InteL-VAEs).…

Machine Learning · Statistics 2022-02-16 Ning Miao , Emile Mathieu , N. Siddharth , Yee Whye Teh , Tom Rainforth

This paper investigates fake news detection as a downstream evaluation of Transformer representations, benchmarking encoder-only and decoder-only pre-trained models (BERT, GPT-2, Transformer-XL) as frozen embedders paired with lightweight…

Computation and Language · Computer Science 2025-12-01 Sumit Mamtani , Abhijeet Bhure

Transformer architectures, underpinned by the self-attention mechanism, have achieved state-of-the-art results across numerous natural language processing (NLP) tasks by effectively modeling long-range dependencies. However, the…

Machine Learning · Computer Science 2025-04-15 Andrew Kiruluta , Priscilla Burity , Samantha Williams

Attention-based neural networks, such as Transformers, have become ubiquitous in numerous applications, including computer vision, natural language processing, and time-series analysis. In all kinds of attention networks, the attention maps…

Machine Learning · Computer Science 2023-05-01 Yujing Wang , Yaming Yang , Zhuo Li , Jiangang Bai , Mingliang Zhang , Xiangtai Li , Jing Yu , Ce Zhang , Gao Huang , Yunhai Tong

Attention mechanism has become the dominant module in natural language processing models. It is computationally intensive and depends on massive power-hungry multiplications. In this paper, we rethink variants of attention mechanism from…

Computation and Language · Computer Science 2022-10-20 Yu Wan , Baosong Yang , Dayiheng Liu , Rong Xiao , Derek F. Wong , Haibo Zhang , Boxing Chen , Lidia S. Chao

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

We present the Condensate Theorem: attention sparsity is a learned topological property, not an architectural constraint. Through empirical analysis of trained language models, we find that attention mass concentrates on a distinct…

Machine Learning · Computer Science 2026-02-11 Jorge L. Ruiz Williams

Transformers are increasingly dominating multi-modal reasoning tasks, such as visual question answering, achieving state-of-the-art results thanks to their ability to contextualize information using the self-attention and co-attention…

Computer Vision and Pattern Recognition · Computer Science 2021-03-30 Hila Chefer , Shir Gur , Lior Wolf

Decomposing model activations into interpretable components is a key open problem in mechanistic interpretability. Sparse autoencoders (SAEs) are a popular method for decomposing the internal activations of trained transformers into sparse,…

Machine Learning · Computer Science 2024-06-26 Connor Kissane , Robert Krzyzanowski , Joseph Isaac Bloom , Arthur Conmy , Neel Nanda

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

Many positional encodings (PEs) are designed to exhibit long-term decay, based on an entrenched and long-standing inductive opinion: tokens farther away from the current position carry less relevant information. We argue that long-term…

Computation and Language · Computer Science 2024-12-06 Yuhan Chen , Ang Lv , Jian Luan , Bin Wang , Wei Liu

Unsupervised pre-training on vast amounts of graph data is critical in real-world applications wherein labeled data is limited, such as molecule properties prediction or materials science. Existing approaches pre-train models for specific…

Machine Learning · Computer Science 2024-10-01 Viet Anh Nguyen , Nhat Khang Ngo , Truong Son Hy

We introduce exclusive self attention (XSA), a simple modification of self attention (SA) that improves Transformer's sequence modeling performance. The key idea is to constrain attention to capture only information orthogonal to the…

Machine Learning · Computer Science 2026-03-11 Shuangfei Zhai
‹ Prev 1 3 4 5 6 7 10 Next ›