相关论文: Element-wise Attention Is All You Need

The human brain uses selective attention to filter perceptual input so that only the components that are useful for behaviour are processed using its limited computational resources. We focus on one particular form of visual attention known…

Entity tracking requires maintaining and updating latent states for entities and attributes over long sequences. Recent task-specific attention operators can compress deep Transformer stacks into a few layers by performing multi-hop state…

Linear attention reduces the quadratic cost of softmax attention to $\mathcal{O}(T)$, but its memory state grows as $\mathcal{O}(T)$ in Frobenius norm, causing progressive interference between stored associations. We introduce…

Self-attention-based models have achieved remarkable progress in short-text mining. However, the quadratic computational complexities restrict their application in long text processing. Prior works have adopted the chunking strategy to…

Long-context modeling is crucial for next-generation language models, yet the high computational cost of standard attention mechanisms poses significant computational challenges. Sparse attention offers a promising direction for improving…

Linear Attention (LA) offers a promising paradigm for scaling large language models (LLMs) to long sequences by avoiding the quadratic complexity of self-attention. Recent LA models such as Mamba2 and GDN interpret linear recurrences as…

Large transformer models have shown extraordinary success in achieving state-of-the-art results in many natural language processing applications. However, training and deploying these models can be prohibitively costly for long sequences,…

Recent non-local self-attention methods have proven to be effective in capturing long-range dependencies for semantic segmentation. These methods usually form a similarity map of RC*C (by compressing spatial dimensions) or RHW*HW (by…

In this work, we propose several attention formulations for multivariate sequence data. We build on top of the recently introduced 2D-Attention and reformulate the attention learning methodology by quantifying the relevance of…

Self-attention network, an attention-based feedforward neural network, has recently shown the potential to replace recurrent neural networks (RNNs) in a variety of NLP tasks. However, it is not clear if the self-attention network could be a…

Attention mechanisms have become a core component of deep learning models, with Channel Attention and Spatial Attention being the two most representative architectures. Current research on their fusion strategies primarily bifurcates into…

It is widely accepted from transformer research that "attention is all we need", but the amount of attention required has never been systematically quantified. Is quadratic $O(L^2)$ attention necessary, or is there a sub-quadratic attention…

The attention mechanism is an important reason for the success of transformers. It relies on computing pairwise relations between tokens. To reduce the high computational cost of standard quadratic attention, linear attention has been…

Self-attention (SA) has become the cornerstone of modern vision backbones for its powerful expressivity over traditional Convolutions (Conv). However, its quadratic complexity remains a critical bottleneck for practical applications. Given…

Long-context ability, has become one of the most important iteration direction of next-generation Large Language Models, particularly in semantic understanding/reasoning, code agentic intelligence and recommendation system. However, the…

The design of Large Language Models (LLMs) has long been hampered by a fundamental conflict within their core attention mechanism: its remarkable expressivity is built upon a computational complexity of O(H N^2) that grows quadratically…

Self-attention is a method of encoding sequences of vectors by relating these vectors to each-other based on pairwise similarities. These models have recently shown promising results for modeling discrete sequences, but they are non-trivial…

Transformer-based speech recognition models have achieved great success due to the self-attention (SA) mechanism that utilizes every frame in the feature extraction process. Especially, SA heads in lower layers capture various phonetic…

We propose a new attention mechanism with linear complexity, ATP, that fixates \textbf{A}ttention on \textbf{T}op \textbf{P}rincipal keys, rather than on each individual token. Particularly, ATP is driven by an important observation that…

Over recent years, the Transformer has become a fundamental building block for sequence modeling architectures. Yet at its core is the use of self-attention, whose memory and computational cost grow quadratically with the sequence length…