English
Related papers

Related papers: Thinking While Listening: Fast-Slow Recurrence for…

200 papers

Recent advances in large reasoning models have been driven by reinforcement learning and test-time scaling, accompanied by growing interest in latent rather than purely textual reasoning. However, existing latent reasoning methods lack…

Computation and Language · Computer Science 2026-04-21 Shengmin Piao , Sanghyun Park

Traditional Recurrent Neural Networks (RNNs) and Long Short-Term Memory (LSTM) units operate on discrete time steps, often failing to capture the fluid temporal dynamics of real-world physical processes. Liquid Neural Networks (LNNs),…

Machine Learning · Computer Science 2026-05-28 Ye Kyaw Thu , Thazin Myint Oo , Thepchai Supnithi

Large language models (LLMs) often suffer from catastrophic forgetting in continual learning: after learning new tasks sequentially, they perform worse on earlier tasks. Existing methods mitigate catastrophic forgetting by data replay,…

Machine Learning · Computer Science 2026-05-08 Yazheng Liu , Yuxuan Wan , Rui Xu , Xi Zhang , Sihong Xie , Hui Xiong

The standard LSTM recurrent neural networks while very powerful in long-range dependency sequence applications have highly complex structure and relatively large (adaptive) parameters. In this work, we present empirical comparison between…

Neural and Evolutionary Computing · Computer Science 2017-01-13 Yuzhen Lu , Fathi M. Salem

In this work we present a modification in the conventional flow of information through a LSTM network, which we consider well suited for RNNs in general. The modification leads to a iterative scheme where the computations performed by the…

Machine Learning · Computer Science 2018-07-27 Leandro Palma , Luis Argerich

Large language models (LLMs) often exhibit deficient reasoning or generate hallucinations. To address these, studies prefixed with "Self-" such as Self-Consistency, Self-Improve, and Self-Refine have been initiated. They share a…

Computation and Language · Computer Science 2024-09-19 Xun Liang , Shichao Song , Zifan Zheng , Hanyu Wang , Qingchen Yu , Xunkai Li , Rong-Hua Li , Yi Wang , Zhonghao Wang , Feiyu Xiong , Zhiyu Li

Continual Learning trains models on a stream of data, with the aim of learning new information without forgetting previous knowledge. Given the dynamic nature of such environments, explaining the predictions of these models can be…

Machine Learning · Computer Science 2023-06-21 Andrea Cossu , Francesco Spinnato , Riccardo Guidotti , Davide Bacciu

Large language models (LLMs) increasingly receive information as streams of passages, conversations, and long-context workflows. While longer context windows expose more evidence, they do not ensure that useful information is preserved and…

Computation and Language · Computer Science 2026-05-13 Zekun Wang , Anant Gupta , Zihan Dong , Christopher J. MacLellan

In streaming scenarios, models must learn continuously, adapting to concept drifts without erasing previously acquired knowledge. However, existing research communities address these challenges in isolation. Continual Learning (CL) focuses…

Machine Learning · Computer Science 2025-12-15 Afonso Lourenço , João Gama , Eric P. Xing , Goreti Marreiros

Lifelong Model Editing aims to continuously update evolving facts in Large Language Models while preserving unrelated knowledge and general capabilities, yet it remains plagued by catastrophic forgetting and model collapse. Empirically, we…

Machine Learning · Computer Science 2026-05-13 Xin Ma , Wei Chen , Qi Liu , Derong Xu , Zhi Zheng , Tong Xu , Enhong Chen

Modern machine learning systems need to be able to cope with constantly arriving and changing data. Two main areas of research dealing with such scenarios are continual learning and data stream mining. Continual learning focuses on…

Machine Learning · Computer Science 2021-04-27 Łukasz Korycki , Bartosz Krawczyk

Recurrent Networks are one of the most powerful and promising artificial neural network algorithms to processing the sequential data such as natural languages, sound, time series data. Unlike traditional feed-forward network, Recurrent…

Machine Learning · Computer Science 2018-07-11 Pushparaja Murugan

Recurrent neural networks can learn complex transduction problems that require maintaining and actively exploiting a memory of their inputs. Such models traditionally consider memory and input-output functionalities indissolubly entangled.…

Machine Learning · Computer Science 2018-11-09 Davide Bacciu , Antonio Carta , Alessandro Sperduti

Attention is an important cognition process of humans, which helps humans concentrate on critical information during their perception and learning. However, although many machine learning models can remember information of data, they have…

Machine Learning · Computer Science 2019-09-06 Guoqiang Zhong , Xin Lin , Kang Chen , Qingyang Li , Kaizhu Huang

Recurrent neural networks (RNNs), temporal convolutions, and neural differential equations (NDEs) are popular families of deep learning models for time-series data, each with unique strengths and tradeoffs in modeling power and…

Machine Learning · Computer Science 2021-10-28 Albert Gu , Isys Johnson , Karan Goel , Khaled Saab , Tri Dao , Atri Rudra , Christopher Ré

Sequence-to-sequence learning with neural networks has become the de facto standard for sequence prediction tasks. This approach typically models the local distribution over the next word with a powerful neural network that can condition on…

Computation and Language · Computer Science 2021-11-17 Yoon Kim

LLMs are trained once, then deployed into a world that never stops changing. External memory compensates for this, but most systems manage it explicitly rather than letting it adapt on its own. Biological memory works differently: coupled…

Machine Learning · Computer Science 2026-05-08 Andreas Pattichis , Constantine Dovrolis

Learning continuously during all model lifetime is fundamental to deploy machine learning solutions robust to drifts in the data distribution. Advances in Continual Learning (CL) with recurrent neural networks could pave the way to a large…

Machine Learning · Computer Science 2021-08-03 Andrea Cossu , Antonio Carta , Vincenzo Lomonaco , Davide Bacciu

Transformers exhibit compositional reasoning on sequences not observed during training, a capability often attributed to in-context learning (ICL) and skill composition. We investigate this phenomenon using the Random Hierarchy Model (RHM),…

Machine Learning · Computer Science 2025-10-21 Jing Liu

Reliably counting and generating sequences of items remain a significant challenge for neural networks, including Large Language Models (LLMs). Indeed, although this capability is readily handled by rule-based symbolic systems based on…

Artificial Intelligence · Computer Science 2026-01-14 Kuinan Hou , Marco Zorzi , Alberto Testolin