English
Related papers

Related papers: Transformers in Uniform TC$^0$

200 papers

We revisit the design choices in Transformers, and propose methods to address their weaknesses in handling long sequences. First, we propose a simple layer named gated attention unit, which allows the use of a weaker single-head attention…

Machine Learning · Computer Science 2022-06-28 Weizhe Hua , Zihang Dai , Hanxiao Liu , Quoc V. Le

Transformers have emerged as the dominant neural-network architecture, achieving state-of-the-art performance in language processing and computer vision. At the core of these models lies the attention mechanism, which requires a nonlinear,…

Machine Learning · Computer Science 2026-04-13 Luis Mickeler , Kai Lion , Alfonso Nardi , Jost Kellner , Pierre Didier , Bhavin J. Shastri , Niao He , Rachel Grange

The ability to reason lies at the core of artificial intelligence (AI), and challenging problems usually call for deeper and longer reasoning to tackle. A crucial question about AI reasoning is whether models can extrapolate learned…

Machine Learning · Computer Science 2025-11-11 Yu Huang , Zixin Wen , Aarti Singh , Yuejie Chi , Yuxin Chen

Transformer-based architectures traditionally employ softmax to compute attention weights, which produces dense distributions over all tokens in a sequence. While effective in many settings, this density has been shown to be detrimental for…

Computation and Language · Computer Science 2026-03-03 Pavlo Vasylenko , Hugo Pitorro , André F. T. Martins , Marcos Treviso

Despite its original goal to jointly learn to align and translate, prior researches suggest that Transformer captures poor word alignments through its attention mechanism. In this paper, we show that attention weights DO capture accurate…

Computation and Language · Computer Science 2020-12-04 Yun Chen , Yang Liu , Guanhua Chen , Xin Jiang , Qun Liu

Transformers are slow and memory-hungry on long sequences, since the time and memory complexity of self-attention are quadratic in sequence length. Approximate attention methods have attempted to address this problem by trading off model…

Machine Learning · Computer Science 2022-06-24 Tri Dao , Daniel Y. Fu , Stefano Ermon , Atri Rudra , Christopher Ré

Transformer-based models have emerged as one of the most widely used architectures for natural language processing, natural language generation, and image generation. The size of the state-of-the-art models has increased steadily reaching…

Hardware Architecture · Computer Science 2025-01-15 Rya Sanovar , Srikant Bharadwaj , Renee St. Amant , Victor Rühle , Saravan Rajmohan

In modern machine learning, inner product attention computation is a fundamental task for training large language models such as Transformer, GPT-1, BERT, GPT-2, GPT-3 and ChatGPT. Formally, in this problem, one is given as input three…

Machine Learning · Computer Science 2023-05-11 Josh Alman , Zhao Song

Transformers with linear attention allow for efficient parallel training but can simultaneously be formulated as an RNN with 2D (matrix-valued) hidden states, thus enjoying linear-time inference complexity. However, linear attention…

Machine Learning · Computer Science 2024-08-28 Songlin Yang , Bailin Wang , Yikang Shen , Rameswar Panda , Yoon Kim

Transformer-based large language models (LLMs) have achieved strong performance across many natural language processing tasks. Nonetheless, their quadratic computational and memory requirements, particularly in self-attention layers, pose…

Computation and Language · Computer Science 2025-09-03 Fabien Furfaro

Efficiently supporting long context length is crucial for Transformer models. The quadratic complexity of the self-attention computation plagues traditional Transformers. Sliding window-based static sparse attention mitigates the problem by…

Hardware Architecture · Computer Science 2024-05-28 Zhenyu Bai , Pranav Dangi , Huize Li , Tulika Mitra

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…

Machine Learning · Computer Science 2024-04-30 Franz A. Heinsen

The quadratic cost of attention in transformers motivated the development of efficient approaches: namely sparse and sliding window attention, convolutions and linear attention. Although these approaches result in impressive reductions in…

Machine Learning · Computer Science 2025-11-10 Jatin Prakash , Aahlad Puli , Rajesh Ranganath

Transformers struggle with length generalisation, displaying poor performance even on basic tasks. We test whether these limitations can be explained through two key failures of the self-attention mechanism. The first is the inability to…

Machine Learning · Computer Science 2025-10-07 Mattia Opper , Roland Fernandez , Paul Smolensky , Jianfeng Gao

The sparse transformer can reduce the computational complexity of the self-attention layers to $O(n)$, whilst still being a universal approximator of continuous sequence-to-sequence functions. However, this permutation variant operation is…

Machine Learning · Computer Science 2023-03-01 Shidi Li , Christian Walder , Alexander Soen , Lexing Xie , Miaomiao Liu

This paper investigates the learning theory of Transformer networks for regression tasks on the compact Euclidean domain $[0,1]^d$ and $d$-dimensional compact Riemannian manifolds. We propose a novel constructive approximation framework for…

Machine Learning · Statistics 2026-05-12 Zhongjie Shi , Wenjing Liao

We propose the first method to show theoretical limitations for one-layer softmax transformers with arbitrarily many precision bits (even infinite). We establish those limitations for three tasks that require advanced reasoning. The first…

This paper introduces THUMT, an open-source toolkit for neural machine translation (NMT) developed by the Natural Language Processing Group at Tsinghua University. THUMT implements the standard attention-based encoder-decoder framework on…

Computation and Language · Computer Science 2017-06-21 Jiacheng Zhang , Yanzhuo Ding , Shiqi Shen , Yong Cheng , Maosong Sun , Huanbo Luan , Yang Liu

While transformer models exhibit strong in-context learning (ICL) abilities, they often fail to generalize under simple distribution shifts. We analyze these failures and identify Softmax, the scoring function in the attention mechanism, as…

Computation and Language · Computer Science 2026-05-12 Omar Naim , Swarnadeep Bhar , Jérôme Bolte , Nicholas Asher

Transformer architectures have emerged as promising deep learning (DL) tools for modeling complex sequence-to-sequence interactions in channel decoding. However, current transformer-based decoders for error correction codes (ECCs)…

Signal Processing · Electrical Eng. & Systems 2025-07-22 Hongzhi Zhu , Wei Xu , Xiaohu You