Related papers: Long Sequence Modeling with Attention Tensorizatio…
Training causal transformers at extreme sequence lengths is bottlenecked by the quadratic time and memory of scaled dot-product attention (SDPA). In this work, we propose Lighthouse Attention, a training-only symmetrical selection-based…
Transformer-based large language models (LLMs) exhibit impressive performance in generative tasks but also introduce significant challenges in real-world serving due to inefficient use of the expensive, computation-optimized accelerators.…
Large Transformer models routinely achieve state-of-the-art results on a number of tasks but training these models can be prohibitively costly, especially on long sequences. We introduce two techniques to improve the efficiency of…
This paper presents a novel fusion method for integrating an external language model (LM) into the Transformer based sequence-to-sequence (seq2seq) model. While paired data are basically required to train the seq2seq model, the external LM…
Transformer has become ubiquitous in the deep learning field. One of the key ingredients that destined its success is the self-attention mechanism, which allows fully-connected contextual encoding over input tokens. However, despite its…
Transformer-based models have achieved state-of-the-art results in a wide range of natural language processing (NLP) tasks including document summarization. Typically these systems are trained by fine-tuning a large pre-trained model to the…
In this paper we address the question of how to render sequence-level networks better at handling structured input. We propose a machine reading simulator which processes text incrementally from left to right and performs shallow reasoning…
This paper addresses the challenges of mining latent patterns and modeling contextual dependencies in complex sequence data. A sequence pattern mining algorithm is proposed by integrating Bidirectional Long Short-Term Memory (BiLSTM) with a…
Attention-based models have been widely used in many areas, such as computer vision and natural language processing. However, relevant applications in time series classification (TSC) have not been explored deeply yet, causing a significant…
Transformer is a powerful model for text understanding. However, it is inefficient due to its quadratic complexity to input sequence length. Although there are many methods on Transformer acceleration, they are still either inefficient on…
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…
The attention module, which is a crucial component in Transformer, cannot scale efficiently to long sequences due to its quadratic complexity. Many works focus on approximating the dot-then-exponentiate softmax function in the original…
While Transformers have revolutionized deep learning, their quadratic attention complexity hinders their ability to process infinitely long inputs. We propose Feedback Attention Memory (FAM), a novel Transformer architecture that leverages…
Transformer achieves promising results on various tasks. However, self-attention suffers from quadratic memory requirements with respect to the sequence length. Existing work focuses on reducing time and space complexity from an algorithm…
Effectively processing long contexts is a critical challenge for language models. While standard Transformers are limited by quadratic complexity and poor length extrapolation, alternative architectures like sliding window attention and…
This paper studies the computational challenges of large-scale attention-based models in artificial intelligence by utilizing importance sampling methods in the streaming setting. Inspired by the classical definition of the $\ell_2$ sampler…
The quadratic computational complexity of standard attention mechanisms presents a severe scalability bottleneck for LLMs in long-context scenarios. While hybrid attention mechanisms combining Full Attention (FA) and Sparse Attention (SA)…
Recent work has shown that either (1) increasing the input length or (2) increasing model size can improve the performance of Transformer-based neural models. In this paper, we present a new model, called LongT5, with which we explore the…
Sequence parallelism (SP), which divides the sequence dimension of input tensors across multiple computational devices, is becoming key to unlocking the long-context capabilities of generative AI models. This paper investigates the…
Transformers are state-of-the-art models for a variety of sequence modeling tasks. At their core is an attention function which models pairwise interactions between the inputs at every timestep. While attention is powerful, it does not…