English
Related papers

Related papers: Efficient Continual Learning in Language Models vi…

200 papers

Large Language Models (LLMs) struggle to handle long input sequences due to high memory and runtime costs. Memory-augmented models have emerged as a promising solution to this problem, but current methods are hindered by limited memory…

Computation and Language · Computer Science 2024-02-22 Zexue He , Leonid Karlinsky , Donghyun Kim , Julian McAuley , Dmitry Krotov , Rogerio Feris

Our brains extract durable, generalizable knowledge from transient experiences of the world. Artificial neural networks come nowhere close to this ability. When tasked with learning to classify objects by training on non-repeating video…

Computer Vision and Pattern Recognition · Computer Science 2024-01-03 Morgan B. Talbot , Rushikesh Zawar , Rohil Badkundri , Mengmi Zhang , Gabriel Kreiman

Continual learning aims to sequentially learn new tasks without forgetting previous tasks' knowledge (catastrophic forgetting). One factor that can cause forgetting is the interference between the gradients on losses from different tasks.…

Computation and Language · Computer Science 2025-12-01 Xueying Bai , Jinghuan Shang , Yifan Sun , Niranjan Balasubramanian

We introduce Neuro-Symbolic Continual Learning, where a model has to solve a sequence of neuro-symbolic tasks, that is, it has to map sub-symbolic inputs to high-level concepts and compute predictions by reasoning consistently with prior…

Machine Learning · Computer Science 2023-12-20 Emanuele Marconato , Gianpaolo Bontempo , Elisa Ficarra , Simone Calderara , Andrea Passerini , Stefano Teso

Continual learning requires balancing plasticity and stability while mitigating catastrophic forgetting. Inspired by human dreaming as a mechanism for internal simulation and knowledge restructuring, we introduce Dream2Learn (D2L), a…

Large language models (LLMs) show an innate skill for solving language based tasks. But insights have suggested an inability to adjust for information or task-solving skills becoming outdated, as their knowledge, stored directly within…

Computation and Language · Computer Science 2024-04-16 Jerry Huang , Prasanna Parthasarathi , Mehdi Rezagholizadeh , Sarath Chandar

Continual Learning (CL) enables machine learning models to learn from continuously shifting new training data in absence of data from old tasks. Recently, pretrained vision transformers combined with prompt tuning have shown promise for…

Computer Vision and Pattern Recognition · Computer Science 2024-04-01 Anurag Roy , Riddhiman Moulick , Vinay K. Verma , Saptarshi Ghosh , Abir Das

The ability to learn in dynamic, nonstationary environments without forgetting previous knowledge, also known as Continual Learning (CL), is a key enabler for scalable and trustworthy deployments of adaptive solutions. While the importance…

Machine Learning · Computer Science 2021-03-25 Andrea Cossu , Antonio Carta , Davide Bacciu

Continual Learning (CL) aims to enable models to continuously acquire new knowledge from a sequence of tasks with avoiding the forgetting of learned information. However, existing CL methods only rely on the parameters of the most recent…

Machine Learning · Computer Science 2025-10-24 Haomiao Qiu , Miao Zhang , Ziyue Qiao , Liqiang Nie

Continuously learning new tasks using high-level ideas or knowledge is a key capability of humans. In this paper, we propose Lifelong reinforcement learning with Sequential linear temporal logic formulas and Reward Machines (LSRM), which…

Artificial Intelligence · Computer Science 2021-11-19 Xuejing Zheng , Chao Yu , Chen Chen , Jianye Hao , Hankz Hankui Zhuo

We propose ThalNet, a deep learning model inspired by neocortical communication via the thalamus. Our model consists of recurrent neural modules that send features through a routing center, endowing the modules with the flexibility to share…

Machine Learning · Computer Science 2017-11-07 Danijar Hafner , Alex Irpan , James Davidson , Nicolas Heess

While end-to-end neural conversation models have led to promising advances in reducing hand-crafted features and errors induced by the traditional complex system architecture, they typically require an enormous amount of data due to the…

Computation and Language · Computer Science 2018-01-10 Sungjin Lee

Deep neural networks often suffer from a critical limitation known as catastrophic forgetting, where performance on past tasks degrades after learning new ones. This paper introduces a novel continual learning approach inspired by human…

Machine Learning · Computer Science 2025-09-16 Prital Bamnodkar

Effective planning in model-based reinforcement learning (MBRL) and model-predictive control (MPC) relies on the accuracy of the learned dynamics model. In many instances of MBRL and MPC, this model is assumed to be stationary and is…

Machine Learning · Computer Science 2026-05-27 Yizhou Huang , Kevin Xie , Homanga Bharadhwaj , Florian Shkurti

In lifelong learning systems based on artificial neural networks, one of the biggest obstacles is the inability to retain old knowledge as new information is encountered. This phenomenon is known as catastrophic forgetting. In this paper,…

Machine Learning · Computer Science 2022-08-16 Alexander Ororbia , Ankur Mali , Daniel Kifer , C. Lee Giles

Continual reinforcement learning must balance retention with adaptation, yet many methods still rely on \emph{single-model preservation}, committing to one evolving policy as the main reusable solution across tasks. Even when a previously…

Machine Learning · Computer Science 2026-04-20 Lute Lillo , Nick Cheney

The cerebellum and cerebral cortex form tightly coupled circuits thought to support flexible and efficient temporal processing. How this interaction shapes cortical learning dynamics, and whether such heterogeneous modularity can benefit…

Neurons and Cognition · Quantitative Biology 2026-05-12 Alexandra Voce , Emmanouil Giannakakis , Claudia Clopath

This paper considers continual learning of large-scale pretrained neural machine translation model without accessing the previous training data or introducing model separation. We argue that the widely used regularization-based methods,…

Computation and Language · Computer Science 2022-11-07 Shuhao Gu , Bojie Hu , Yang Feng

Deep learning models generally display catastrophic forgetting when learning new data continuously. Many incremental learning approaches address this problem by reusing data from previous tasks while learning new tasks. However, the direct…

Machine Learning · Computer Science 2024-11-12 Young Jo Choi , Min Kyoon Yoo , Yu Rang Park

Contextual memory integration remains a high challenge in the development of language models, particularly in tasks that require maintaining coherence over extended sequences. Traditional approaches, such as self-attention mechanisms and…

Computation and Language · Computer Science 2025-08-11 George Applegarth , Christian Weatherstone , Maximilian Hollingsworth , Henry Middlebrook , Marcus Irvin