English
Related papers

Related papers: Selective Induction Heads: How Transformers Select…

200 papers

Transformers have proven highly effective across various applications, especially in handling sequential data such as natural languages and time series. However, transformer models often lack clear interpretability, and the success of…

Machine Learning · Computer Science 2025-12-01 Wei Shi , Yuan Cao

Exploiting data invariances is crucial for efficient learning in both artificial and biological neural circuits. Understanding how neural networks can discover appropriate representations capable of harnessing the underlying symmetries of…

Disordered Systems and Neural Networks · Physics 2022-10-17 Alessandro Ingrosso , Sebastian Goldt

Language modeling has shown us that transformers can discover latent structure from context, but the dynamics of how they acquire different components of that structure remain poorly understood, leading to assertions that models just remix…

Machine Learning · Computer Science 2026-04-23 Rohan Saha , Farzane Aminmansour , Alona Fyshe

In-context learning (ICL) refers to a remarkable capability of pretrained large language models, which can learn a new task given a few examples during inference. However, theoretical understanding of ICL is largely under-explored,…

Machine Learning · Computer Science 2024-09-27 Tong Yang , Yu Huang , Yingbin Liang , Yuejie Chi

In-context learning (ICL) derives its power from enabling Large Language Models to adapt to new tasks via prompt-based reasoning alone, entirely bypassing the need for parameter updates. Existing theories primarily study ICL in single-task…

Machine Learning · Computer Science 2026-05-28 Guangyu Li , Meng Ding , Lijie Hu

Sequence-to-sequence models have achieved impressive results on various tasks. However, they are unsuitable for tasks that require incremental predictions to be made as more data arrives or tasks that have long input sequences and output…

Machine Learning · Computer Science 2016-08-08 Navdeep Jaitly , David Sussillo , Quoc V. Le , Oriol Vinyals , Ilya Sutskever , Samy Bengio

Transformers are built upon multi-head scaled dot-product attention and positional encoding, which aim to learn the feature representations and token dependencies. In this work, we focus on enhancing the distinctive representation by…

Computer Vision and Pattern Recognition · Computer Science 2022-07-12 Litao Yu , Jian Zhang

Transformer-based Large Language Models (LLMs) have demonstrated powerful in-context learning capabilities. However, their predictions can be disrupted by factually correct context, a phenomenon known as context hijacking, revealing a…

Computation and Language · Computer Science 2025-02-24 Tianle Li , Chenyang Zhang , Xingwu Chen , Yuan Cao , Difan Zou

The in-context learning capabilities of modern language models have motivated a deeper mathematical understanding of sequence models. A line of recent work has shown that linear attention models can emulate projected gradient descent…

Computation and Language · Computer Science 2025-03-06 Xiangyu Chang , Yingcong Li , Muti Kara , Samet Oymak , Amit K. Roy-Chowdhury

Recurrent neural networks are effective models to process sequences. However, they are unable to learn long-term dependencies because of their inherent sequential nature. As a solution, Vaswani et al. introduced the Transformer, a model…

Machine Learning · Computer Science 2023-03-28 Quentin Fournier , Gaétan Marceau Caron , Daniel Aloise

The Transformer architecture has become a cornerstone of modern artificial intelligence, but its core self-attention mechanism suffers from a complexity bottleneck that scales quadratically with sequence length, severely limiting its…

Machine Learning · Computer Science 2025-08-29 Zhongpan Tang

Non-stationary sequences arise naturally in control, forecasting, and decision-making. The data-generating process shifts at unknown times, and models must detect the change, discard or downweight obsolete evidence, and adapt to new…

Machine Learning · Computer Science 2026-04-21 Carson Dudley , Yutong Bi , Xiaofeng Liu , Samet Oymak

In recent years, transformer-based models have revolutionized deep learning, particularly in sequence modeling. To better understand this phenomenon, there is a growing interest in using Markov input processes to study transformers.…

Machine Learning · Computer Science 2024-06-28 Ashok Vardhan Makkuva , Marco Bondaschi , Chanakya Ekbote , Adway Girish , Alliot Nagle , Hyeji Kim , Michael Gastpar

Since its introduction, the transformer has shifted the development trajectory away from traditional models (e.g., RNN, MLP) in time series forecasting, which is attributed to its ability to capture global dependencies within temporal…

Machine Learning · Computer Science 2025-01-07 Xiwen Chen , Peijie Qiu , Wenhui Zhu , Huayu Li , Hao Wang , Aristeidis Sotiras , Yalin Wang , Abolfazl Razi

Transformers demonstrate impressive performance on a range of reasoning benchmarks. To evaluate the degree to which these abilities are a result of actual reasoning, existing work has focused on developing sophisticated benchmarks for…

Machine Learning · Computer Science 2024-07-02 Jannik Brinkmann , Abhay Sheshadri , Victor Levoso , Paul Swoboda , Christian Bartelt

The ability to process long contexts is crucial for many natural language processing tasks, yet it remains a significant challenge. While substantial progress has been made in enhancing the efficiency of attention mechanisms, there is still…

Computation and Language · Computer Science 2025-03-06 Konstantin Donhauser , Charles Arnal , Mohammad Pezeshki , Vivien Cabannes , David Lopez-Paz , Kartik Ahuja

Transformers have demonstrated a strong ability for in-context learning (ICL), enabling models to solve previously unseen tasks using only example input output pairs provided at inference time. While prior theoretical work has established…

Machine Learning · Computer Science 2026-05-19 Rushil Chandrupatla , Leo Bangayan , Sebastian Leng

While LLMs demonstrate impressive reasoning capabilities, they remain fragile in multi-step logical deduction, where a single transition error can propagate through the entire reasoning chain, leading to unstable performance. In this work,…

Computation and Language · Computer Science 2026-04-23 Seunghyun Park , Yuanyuan Lei

Transformer-based models have shown strong performance in time-series forecasting by leveraging self-attention to model long-range temporal dependencies. However, their effectiveness depends critically on the quality and structure of input…

Machine Learning · Computer Science 2026-02-11 Saurish Nagrath , Saroj Kumar Panigrahy

Although transformers have demonstrated impressive capabilities for in-context learning (ICL) in practice, theoretical understanding of the underlying mechanism that allows transformers to perform ICL is still in its infancy. This work aims…

Machine Learning · Computer Science 2025-05-30 Wei Shen , Ruida Zhou , Jing Yang , Cong Shen