Related papers: Softplus Attention with Re-weighting Boosts Length…
This paper questions whether the strong performance of softmax attention in transformers stems from producing a probability distribution over inputs. Instead, we argue that softmax's effectiveness lies in its implicit regularization of the…
Large multimodal models (LMMs) inherit the self-attention mechanism of pretrained language backbones, yet standard attention can exhibit suboptimal allocation, including cross-modal misallocation between textual and visual evidence and…
The softmax function is crucial in Transformer attention, which normalizes each row of the attention scores with summation to one, achieving superior performances over other alternative functions. However, the softmax function can face a…
Pairwise dot-product self-attention is key to the success of transformers that achieve state-of-the-art performance across a variety of applications in language and vision. This dot-product self-attention computes attention weights among…
Attention mechanisms have raised significant interest in the research community, since they promise significant improvements in the performance of neural network architectures. However, in any specific problem, we still lack a principled…
As the core operator of Transformers, Softmax Attention exhibits excellent global modeling capabilities. However, its quadratic complexity limits its applicability to vision tasks. In contrast, Linear Attention shares a similar formulation…
Connecting large libraries of digitized audio recordings to their corresponding sheet music images has long been a motivation for researchers to develop new cross-modal retrieval systems. In recent years, retrieval systems based on…
Attention mechanisms have become a standard tool for sequence modeling tasks, in particular by stacking self-attention layers over the entire input sequence as in the Transformer architecture. In this work we introduce a novel attention…
Transformers have achieved significant success across various domains, relying on self-attention to capture dependencies. However, the standard first-order attention mechanism is often limited by a low-rank bottleneck, struggling to capture…
We study two strange phenomena in auto-regressive Transformers: (1) the dominance of the first token in attention heads; (2) the occurrence of large outlier activations in the hidden states. We find that popular large language models, such…
Attention based models such as Transformers involve pairwise interactions between data points, modeled with a learnable attention matrix. Importantly, this attention matrix is normalized with the SoftMax operator, which makes it row-wise…
Unneeded elements in the attention's context degrade performance. We introduce Selective Attention, a simple parameter-free change to the standard attention mechanism which reduces attention to unneeded elements. Selective attention…
The self-attention mechanism is central to the success of Transformer architectures. However, standard row-stochastic attention has been shown to suffer from significant signal degradation across layers. In particular, it can induce rank…
Large Vision-Language Models (VLMs) have achieved remarkable success in multi-modal reasoning, but their inference time efficiency remains a significant challenge due to the memory overhead during decoding, especially when the query and…
In recent years, the attention mechanism contributes significantly to hypergraph based neural networks. However, these methods update the attention weights with the network propagating. That is to say, this type of attention mechanism is…
We propose a simple modification to the conventional attention mechanism applied by Transformers: Instead of quantifying pairwise query-key similarity with scaled dot-products, we quantify it with the logarithms of scaled dot-products of…
Large language models (LLMs) have demonstrated remarkable performance across a wide range of tasks. However, the quadratic complexity of softmax attention remains a central bottleneck that limits their scalability. Alman and Song (NeurIPS…
Attention mechanism is contributing to the majority of recent advances in machine learning for natural language processing. Additionally, it results in an attention map that shows the proportional influence of each input in its decision.…
Convolutional layers are an integral part of many deep neural network solutions in computer vision. Recent work shows that replacing the standard convolution operation with mechanisms based on self-attention leads to improved performance on…
Transformers and deep state space models (SSMs) sit at opposite ends of a basic design choice: attention routes each query through a growing key-value (KV) cache by content-based matching at quadratic cost, while deep SSMs compress context…