Related papers: Sparse Query Attention (SQA): A Computationally Ef…

The pursuit of reducing the memory footprint of the self-attention mechanism in multi-headed self attention (MHA) spawned a rich portfolio of methods, e.g., group-query attention (GQA) and multi-head latent attention (MLA). The methods…

By integrating the self-attention capability and the biological properties of Spiking Neural Networks (SNNs), Spikformer applies the flourishing Transformer architecture to SNNs design. It introduces a Spiking Self-Attention (SSA) module to…

Transformers have revolutionized natural language processing, but their quadratic complexity with respect to sequence length remains a fundamental bottleneck for long-range modeling. While sparse attention mechanisms like RingAttention…

Self-attention scales quadratically with input size, limiting its use for large-scale physical systems. Although sparse attention mechanisms provide a viable alternative, they are primarily designed for regular structures such as text or…

The Transformer architecture has significantly advanced natural language processing (NLP) and has been foundational in developing large language models (LLMs) such as LLaMA and OPT, which have come to dominate a broad range of NLP tasks.…

Dynamic sparse attention (DSA) reduces the per-token attention bandwidth by restricting computation to a top-k subset of cached key-value (KV) entries, but its token-dependent selection pattern introduces a system-level challenge: the KV…

Visual attention mechanisms are widely used in multimodal tasks, as visual question answering (VQA). One drawback of softmax-based attention mechanisms is that they assign some probability mass to all image regions, regardless of their…

Transformers have dominated sequence processing tasks for the past seven years -- most notably language modeling. However, the inherent quadratic complexity of their attention mechanism remains a significant bottleneck as context length…

We introduce SA-DQAS, a novel framework that enhances Differentiable Quantum Architecture Search (DQAS) by integrating a self-attention mechanism, enabling more effective quantum circuit design for variational quantum algorithms. Unlike…

Long-sequence processing is a critical capability for modern large language models. However, the self-attention mechanism in the standard Transformer architecture faces severe computational and memory bottlenecks when processing long…

In this work, we conduct a systematic analysis of Native Sparse Attention (NSA) and propose targeted improvements that enhance long-context modeling. A key insight is that alternating between local (sliding-window) and global (compression,…

Multi-Head Attention (MHA) is a key component of Transformer. In MHA, attention heads work independently, causing problems such as low-rank bottleneck of attention score matrices and head redundancy. We propose Dynamically Composable…

Vision Transformers (ViT) serve as powerful vision models. Unlike convolutional neural networks, which dominated vision research in previous years, vision transformers enjoy the ability to capture long-range dependencies in the data.…

The state-of-the-art speech enhancement has limited performance in speech estimation accuracy. Recently, in deep learning, the Transformer shows the potential to exploit the long-range dependency in speech by self-attention. Therefore, it…

Attention scales quadratically with sequence length, fundamentally limiting long-context inference. Existing block-granularity sparsification can reduce latency, but coarse blocks impose an intrinsic sparsity ceiling, making further…

Transformers have demonstrated great success in numerous domains including natural language processing and bioinformatics. This success stems from the use of the attention mechanism by these models in order to represent and propagate…

Converting pretrained attention modules such as grouped-query attention (GQA) into multi-head latent attention (MLA) can improve expressivity without increasing KV-cache cost, making it attractive for efficient inference. However, many…

We introduce Monte-Carlo Attention (MCA), a randomized approximation method for reducing the computational cost of self-attention mechanisms in Transformer architectures. MCA exploits the fact that the importance of each token in an input…

Recently, it has been argued that encoder-decoder models can be made more interpretable by replacing the softmax function in the attention with its sparse variants. In this work, we introduce a novel, simple method for achieving sparsity in…

The success of the self-attention mechanism in classical machine learning models has inspired the development of quantum analogs aimed at reducing computational overhead. Self-attention integrates learnable query and key matrices to…