Related papers: Value-aware Approximate Attention
Vision Transformers have achieved impressive performance in video classification, while suffering from the quadratic complexity caused by the Softmax attention mechanism. Some studies alleviate the computational costs by reducing the number…
Transformers flexibly operate over sets of real-valued vectors representing task-specific entities and their attributes, where each vector might encode one word-piece token and its position in a sequence, or some piece of information that…
We propose a novel attention model that can accurately attends to target objects of various scales and shapes in images. The model is trained to gradually suppress irrelevant regions in an input image via a progressive attentive process…
Transformers' quadratic complexity with respect to the input sequence length has motivated a body of work on efficient sparse approximations to softmax. An alternative path, used by entmax transformers, consists of having built-in exact…
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…
Interpretability is an important aspect of the trustworthiness of a model's predictions. Transformer's predictions are widely explained by the attention weights, i.e., a probability distribution generated at its self-attention unit (head).…
The quadratic complexity of self-attention in Transformer models remains a significant bottleneck for processing long sequences and deploying large language models efficiently. For this approach, there has been significant research into…
We introduce Attention Free Transformer (AFT), an efficient variant of Transformers that eliminates the need for dot product self attention. In an AFT layer, the key and value are first combined with a set of learned position biases, the…
Sparse Attention is a technique that approximates standard attention computation with sub-quadratic complexity. This is achieved by selectively ignoring smaller entries in the attention matrix during the softmax function computation.…
How much information do NLP tasks really need from a transformer's attention mechanism at application-time (inference)? From recent work, we know that there is sparsity in transformers and that the floating-points within its computation can…
Transformer networks have lead to important progress in language modeling and machine translation. These models include two consecutive modules, a feed-forward layer and a self-attention layer. The latter allows the network to capture long…
Transformer architectures have achieved remarkable success across language, vision, and multimodal tasks, and there is growing demand for them to address in-context compositional learning tasks. In these tasks, models solve the target…
This work aims to improve the efficiency of vision transformers (ViT). While ViTs use computationally expensive self-attention operations in every layer, we identify that these operations are highly correlated across layers -- a key…
Transformer has been widely-used in many Natural Language Processing (NLP) tasks and the scaled dot-product attention between tokens is a core module of Transformer. This attention is a token-wise design and its complexity is quadratic to…
Unlike Object Detection, Visual Grounding task necessitates the detection of an object described by complex free-form language. To simultaneously model such complex semantic and visual representations, recent state-of-the-art studies adopt…
Scaling the context size of large language models (LLMs) enables them to perform various new tasks, e.g., book summarization. However, the memory cost of the Key and Value (KV) cache in attention significantly limits the practical…
Transformer-based architectures have become the prevailing backbone of large language models. However, the quadratic time and memory complexity of self-attention remains a fundamental obstacle to efficient long-context modeling. To address…
Sentence representations are foundational to many Natural Language Processing (NLP) applications. While recent methods leverage Large Language Models (LLMs) to derive sentence representations, most rely on final-layer hidden states, which…
Self-attention weights and their transformed variants have been the main source of information for analyzing token-to-token interactions in Transformer-based models. But despite their ease of interpretation, these weights are not faithful…
Vision Transformers are very popular nowadays due to their state-of-the-art performance in several computer vision tasks, such as image classification and action recognition. Although their performance has been greatly enhanced through…