English
Related papers

Related papers: One-layer transformers fail to solve the induction…

200 papers

State of the art sequence-to-sequence models for large scale tasks perform a fixed number of computations for each input sequence regardless of whether it is easy or hard to process. In this paper, we train Transformer models which can make…

Computation and Language · Computer Science 2020-02-18 Maha Elbayad , Jiatao Gu , Edouard Grave , Michael Auli

Large Language Models (LLMs) are becoming increasingly popular in pervasive computing due to their versatility and strong performance. However, despite their ubiquitous use, the exact mechanisms underlying their outstanding performance…

Computation and Language · Computer Science 2026-02-02 Alhassan Abdelhalim , Janick Edinger , Sören Laue , Michaela Regneri

The computational complexity of the self-attention mechanism in popular transformer architectures poses significant challenges for training and inference, and becomes the bottleneck for long inputs. Is it possible to significantly reduce…

Machine Learning · Computer Science 2024-10-16 Yingyu Liang , Zhizhou Sha , Zhenmei Shi , Zhao Song , Yufa Zhou

Top-down tree transducers are a convenient formalism for describing tree transformations. They can be equipped with regular look-ahead, which allows them to inspect a subtree before processing it. In certain cases, such a look-ahead can be…

Formal Languages and Automata Theory · Computer Science 2015-12-04 Joost Engelfriet , Sebastian Maneth , Helmut Seidl

Despite the remarkable success of transformer-based models in various real-world tasks, their underlying mechanisms remain poorly understood. Recent studies have suggested that transformers can implement gradient descent as an in-context…

Machine Learning · Computer Science 2024-08-09 Xingwu Chen , Lei Zhao , Difan Zou

Transformer has become the dominant architecture for sequence modeling, yet a detailed understanding of how its structural parameters influence expressive power remains limited. In this work, we study the approximation properties of…

Machine Learning · Computer Science 2026-04-01 Penghao Yu , Haotian Jiang , Zeyu Bao , Ruoxi Yu , Qianxiao Li

In contrast with previous approaches where information flows only towards deeper layers of a stack, we consider a multi-pass transformer (MPT) architecture in which earlier layers are allowed to process information in light of the output of…

Computation and Language · Computer Science 2020-09-25 Peng Gao , Chiori Hori , Shijie Geng , Takaaki Hori , Jonathan Le Roux

Transformers have been successfully used in various fields and are becoming the standard tools in computer vision. However, self-attention, a core component of transformers, has a quadratic complexity problem, which limits the use of…

Computer Vision and Pattern Recognition · Computer Science 2022-06-02 Jiuk Hong , Chaehyeon Lee , Soyoun Bang , Heechul Jung

Attention-based transformers have achieved tremendous success across a variety of disciplines including natural languages. To deepen our understanding of their sequential modeling capabilities, there is a growing interest in using Markov…

Machine Learning · Computer Science 2025-07-22 Ashok Vardhan Makkuva , Marco Bondaschi , Adway Girish , Alliot Nagle , Martin Jaggi , Hyeji Kim , Michael Gastpar

The decidability of equivalence for three important classes of tree transducers is discussed. Each class can be obtained as a natural restriction of deterministic macro tree transducers (MTTs): (1) no context parameters, i.e., top-down tree…

Formal Languages and Automata Theory · Computer Science 2014-05-23 Sebastian Maneth

We study how information propagates in decoder-only Transformers, which are the architectural backbone of most existing frontier large language models (LLMs). We rely on a theoretical signal propagation analysis -- specifically, we analyse…

It is staggering that words of the English language, which are on average represented by 5--6 bytes of ASCII, require as much as 24 kilobytes when served to large language models. We show that there is room for more information in every…

Machine Learning · Computer Science 2024-11-01 Peter Belcak , Roger Wattenhofer

This paper investigates approximation-theoretic aspects of the in-context learning capability of the transformers in representing a family of noisy linear dynamical systems. Our first theoretical result establishes an upper bound on the…

Machine Learning · Computer Science 2025-10-22 Frank Cole , Yuxuan Zhao , Yulong Lu , Tianhao Zhang

We investigate whether transformers use their depth adaptively across tasks of increasing difficulty. Using a controlled multi-hop relational reasoning task based on family stories, where difficulty is determined by the number of…

Machine Learning · Computer Science 2026-04-15 Alicia Curth , Rachel Lawrence , Sushrut Karmalkar , Niranjani Prasad

Learning representations on large-sized graphs is a long-standing challenge due to the inter-dependence nature involved in massive data points. Transformers, as an emerging class of foundation encoders for graph-structured data, have shown…

Machine Learning · Computer Science 2024-08-19 Qitian Wu , Wentao Zhao , Chenxiao Yang , Hengrui Zhang , Fan Nie , Haitian Jiang , Yatao Bian , Junchi Yan

The transformer architecture has become the foundation of modern Large Language Models (LLMs), yet its theoretical properties are still not well understood. As with classic neural networks, a common approach to improve these models is to…

Artificial Intelligence · Computer Science 2025-09-26 Álvaro Rodríguez Abella , João Pedro Silvestre , Paulo Tabuada

The advent of transformers has in recent years led to powerful and revolutionary Large Language Models (LLMs). Despite this, our understanding on the capability of transformers is still meager. In this invited contribution, we recount the…

Formal Languages and Automata Theory · Computer Science 2025-09-30 Anthony W. Lin , Pablo Barcelo

Addition is perhaps one of the simplest arithmetic tasks one can think of and is usually performed using the carrying over algorithm. This algorithm consists of two tasks: adding digits in the same position and carrying over a one whenever…

Machine Learning · Computer Science 2024-01-18 Jorrit Kruthoff

Test-time scaling paradigms have significantly advanced the capabilities of large language models (LLMs) on complex tasks. Despite their empirical success, theoretical understanding of the sample efficiency of various test-time strategies…

Machine Learning · Computer Science 2025-06-13 Baihe Huang , Shanda Li , Tianhao Wu , Yiming Yang , Ameet Talwalkar , Kannan Ramchandran , Michael I. Jordan , Jiantao Jiao

In spite of their huge success, transformer models remain difficult to scale in depth. In this work, we develop a unified signal propagation theory and provide formulae that govern the moments of the forward and backward signal through the…

Computation and Language · Computer Science 2024-07-19 Akhil Kedia , Mohd Abbas Zaidi , Sushil Khyalia , Jungho Jung , Harshith Goka , Haejun Lee