English
Related papers

Related papers: Meta-Attention: Bayesian Per-Token Routing for Eff…

200 papers

The most widely used artificial intelligence (AI) models today are Transformers employing self-attention. In its standard form, self-attention incurs costs that increase with context length, driving demand for storage, compute, and energy…

Machine Learning · Computer Science 2026-02-03 Franz A. Heinsen , Leo Kozachkov

Transformer model with multi-head attention requires caching intermediate results for efficient inference in generation tasks. However, cache brings new memory-related costs and prevents leveraging larger batch size for faster speed. We…

Computation and Language · Computer Science 2021-06-15 Yu Yan , Jiusheng Chen , Weizhen Qi , Nikhil Bhendawade , Yeyun Gong , Nan Duan , Ruofei Zhang

The attention mechanism of a transformer has a quadratic complexity, leading to high inference costs and latency for long sequences. However, attention matrices are mostly sparse, which implies that many entries may be omitted from…

Machine Learning · Computer Science 2025-11-25 Jeffrey Willette , Heejun Lee , Sung Ju Hwang

Transformers usually expose one inference cost per trained model, while deployed systems often need multiple cost-quality operating points. We study Budgeted Attention Allocation, a monotone head-gating mechanism conditioned on a requested…

Machine Learning · Computer Science 2026-05-08 Amrit Nidhi

Transformer-based models have emerged as one of the most widely used architectures for natural language processing, natural language generation, and image generation. The size of the state-of-the-art models has increased steadily reaching…

Hardware Architecture · Computer Science 2025-01-15 Rya Sanovar , Srikant Bharadwaj , Renee St. Amant , Victor Rühle , Saravan Rajmohan

Standard inference and training with transformer based architectures scale quadratically with input sequence length. This is prohibitively large for a variety of applications especially in web-page translation, query-answering etc.…

Computation and Language · Computer Science 2023-03-20 Lovish Madaan , Srinadh Bhojanapalli , Himanshu Jain , Prateek Jain

We introduce directional routing, a lightweight mechanism that gives each transformer attention head learned suppression directions controlled by a shared router, at 3.9% parameter cost. We train a 433M-parameter model alongside an…

Machine Learning · Computer Science 2026-03-17 Kevin Taylor

The original softmax-based attention mechanism (regular attention) in the extremely successful Transformer architecture computes attention between $N$ tokens, each embedded in a $D$-dimensional head, with a time complexity of $O(N^2D)$.…

Machine Learning · Computer Science 2025-10-28 Armin Gerami , Ramani Duraiswami

Attention is a key part of the transformer architecture. It is a sequence-to-sequence mapping that transforms each sequence element into a weighted sum of values. The weights are typically obtained as the softmax of dot products between…

Transformers have become the dominant architecture across a wide range of domains, largely due to the effectiveness of multi-head attention in capturing diverse representation subspaces. However, standard multi-head attention activates all…

Machine Learning · Computer Science 2026-04-27 Bilal Faye , Abdoulaye Mbaye , Hanane Azzag , Mustapha Lebbah

Transformers empirically perform precise probabilistic reasoning in carefully constructed ``Bayesian wind tunnels'' and in large-scale language models, yet the mechanisms by which gradient-based learning creates the required internal…

Machine Learning · Statistics 2026-05-19 Naman Agarwal , Siddhartha R. Dalal , Vishal Misra

To overcome the quadratic cost of self-attention, recent works have proposed various sparse attention modules, most of which fall under one of two groups: 1) sparse attention under a hand-crafted patterns and 2) full attention followed by a…

Machine Learning · Computer Science 2022-10-28 Sungjun Cho , Seonwoo Min , Jinwoo Kim , Moontae Lee , Honglak Lee , Seunghoon Hong

Attention is a core component of transformer architecture, whether encoder-only, decoder-only, or encoder-decoder model. However, the standard softmax attention often produces noisy probability distribution, which can impair effective…

Computation and Language · Computer Science 2025-11-11 Dhananjay Ram , Wei Xia , Stefano Soatto

Standard transformer architectures apply the same number of layers to every token regardless of contextual difficulty. We present Token-Selective Attention (TSA), a learned per-token gate on residual updates between consecutive transformer…

Machine Learning · Computer Science 2026-05-08 Ahmed Abdelmuniem Abdalla Mohammed

Attention-based neural networks have achieved state-of-the-art results on a wide range of tasks. Most such models use deterministic attention while stochastic attention is less explored due to the optimization difficulties or complicated…

Machine Learning · Computer Science 2021-06-10 Shujian Zhang , Xinjie Fan , Bo Chen , Mingyuan Zhou

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

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

While self-attention has been instrumental in the success of Transformers, it can lead to over-concentration on a few tokens during training, resulting in suboptimal information flow. Enforcing doubly-stochastic constraints in attention…

Machine Learning · Computer Science 2025-07-15 Ashkan Shahbazi , Elaheh Akbari , Darian Salehi , Xinran Liu , Navid Naderializadeh , Soheil Kolouri

Self-attention has recently been adopted for a wide range of sequence modeling problems. Despite its effectiveness, self-attention suffers from quadratic compute and memory requirements with respect to sequence length. Successful approaches…

Machine Learning · Computer Science 2020-10-27 Aurko Roy , Mohammad Saffar , Ashish Vaswani , David Grangier

The Transformer translation model is based on the multi-head attention mechanism, which can be parallelized easily. The multi-head attention network performs the scaled dot-product attention function in parallel, empowering the model by…

Computation and Language · Computer Science 2021-09-13 Hongfei Xu , Qiuhui Liu , Josef van Genabith , Deyi Xiong
‹ Prev 1 2 3 10 Next ›