English
Related papers

Related papers: Investigating Recurrent Transformers with Dynamic …

200 papers

Standard Transformers excel at semantic modeling but struggle with rigid sequential logic and state tracking. Theoretical work establishes that self-attention is limited to $\AC^0$ (under hard attention) or $\TC^0$ (under soft attention),…

Machine Learning · Computer Science 2026-02-10 Mehryar Mohri

Since its introduction in 2017, Transformer has emerged as the leading neural network architecture, catalyzing revolutionary advancements in many AI disciplines. The key innovation in Transformer is a Self-Attention (SA) mechanism designed…

Machine Learning · Computer Science 2024-02-05 Yueyao Yu , Yin Zhang

Recurrent-depth transformers scale test-time compute by iterating latent computations before emitting tokens. We study the geometry of these iterates and argue for a simple, two-scale operational picture: (i) within a looped block, updates…

Machine Learning · Computer Science 2025-11-14 Francesco Pappone , Donato Crisostomi , Emanuele Rodolà

This paper presents a general iterative bias correction procedure for regression smoothers. This bias reduction schema is shown to correspond operationally to the $L_2$ Boosting algorithm and provides a new statistical interpretation for…

Methodology · Statistics 2008-01-31 Pierre Andre Cornillon , Nicolas Hengartner , Eric Matzner-Lober

Recurrent Neural Networks (RNNs) have shown great success in modeling time-dependent patterns, but there is limited research on their learned representations of latent temporal features and the emergence of these representations during…

Machine Learning · Computer Science 2023-06-13 Peter DelMastro , Rushiv Arora , Edward Rietman , Hava T. Siegelmann

A longstanding challenge for the Machine Learning community is the one of developing models that are capable of processing and learning from very long sequences of data. The outstanding results of Transformers-based networks (e.g., Large…

Machine Learning · Computer Science 2024-02-15 Matteo Tiezzi , Michele Casoni , Alessandro Betti , Tommaso Guidi , Marco Gori , Stefano Melacci

In this paper, we introduce a novel architecture to connecting adaptive learning and neural networks into an arbitrary machine's control system paradigm. Two consecutive Recurrent Neural Networks (RNNs) are used together to accurately model…

Machine Learning · Computer Science 2020-02-26 Srikanth Chandar , Harsha Sunder

While Transformer architectures have demonstrated impressive scalability across domains, they continue to face challenges in long-context reasoning, computational efficiency, and structural generalization - largely due to rigid layer…

Computation and Language · Computer Science 2025-10-03 Haochen You , Baojing Liu

Transformer models systematically favor certain token positions, yet the architectural origins of this position bias remain poorly understood. This bias is closely connected to the Lost-in-the-Middle phenomenon, where models underutilize…

Machine Learning · Computer Science 2026-05-28 Hanna Herasimchyk , Robin Labryga , Tomislav Prusina , Sören Laue

Computational workloads composing traditional transformer models are starkly bifurcated. Multi-Head Attention (MHA) and Grouped-Query Attention are memory-bound due to low arithmetic intensity, while FeedForward Networks are compute-bound.…

Data augmentation is gaining importance across various aspects of time series analysis, from forecasting to classification and anomaly detection tasks. We introduce the Latent Generative Transformer Augmentation (L-GTA) model, a generative…

Machine Learning · Computer Science 2025-08-01 Luis Roque , Carlos Soares , Vitor Cerqueira , Luis Torgo

Recurrent recommender systems have been successful in capturing the temporal dynamics in users' activity trajectories. However, recurrent neural networks (RNNs) are known to have difficulty learning long-term dependencies. As a consequence,…

Information Retrieval · Computer Science 2022-01-27 Bo Chang , Can Xu , Matthieu Lê , Jingchen Feng , Ya Le , Sriraj Badam , Ed Chi , Minmin Chen

In applications such as biomedical studies, epidemiology, and social sciences, recurrent events often co-occur with longitudinal measurements and a terminal event, such as death. Therefore, jointly modeling longitudinal measurements,…

Machine Learning · Statistics 2024-04-08 Zhiyue Zhang , Yao Zhao , Yanxun Xu

This work introduces a new Transformer model called Cached Transformer, which uses Gated Recurrent Cached (GRC) attention to extend the self-attention mechanism with a differentiable memory cache of tokens. GRC attention enables attending…

Computer Vision and Pattern Recognition · Computer Science 2023-12-21 Zhaoyang Zhang , Wenqi Shao , Yixiao Ge , Xiaogang Wang , Jinwei Gu , Ping Luo

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

Scaling model performance typically requires increasing model size. Looped Transformer offers a compelling alternative by iteratively reusing the same Transformer blocks, trading additional computation for improved performance without…

Machine Learning · Computer Science 2026-05-26 Rao Fu , Zixuan Yang , Jiankun Zhang , Jing Ma , Hechang Chen , Yu Li , Yi Chang

Despite the advantageous subquadratic complexity of modern recurrent deep learning models -- such as state-space models (SSMs) -- recent studies have highlighted their potential shortcomings compared to transformers on reasoning and…

Machine Learning · Computer Science 2025-10-13 Destiny Okpekpe , Antonio Orvieto

Language models with recurrent depth, also referred to as universal or looped when considering transformers, are defined by the capacity to increase their computation through the repetition of layers. Recent efforts in pretraining have…

Machine Learning · Computer Science 2025-10-17 Jonas Geiping , Xinyu Yang , Guinan Su

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

Token prediction stability remains a challenge in autoregressive generative models, where minor variations in early inference steps often lead to significant semantic drift over extended sequences. A structured modulation mechanism was…