English
Related papers

Related papers: Efficient Continual Learning in Language Models vi…

200 papers

Large language models (LLMs) excel at many NLP tasks but struggle to sustain long-term interactions due to limited attention over extended dialogue histories. Retrieval-augmented generation (RAG) mitigates this issue but lacks reliable…

Computation and Language · Computer Science 2026-01-23 Chunliang Chen , Ming Guan , Xiao Lin , Jiaxu Li , Luxi Lin , Qiyi Wang , Xiangyu Chen , Jixiang Luo , Changzhi Sun , Dell Zhang , Xuelong Li

Vision-language models (VLMs) have achieved remarkable advancements, capitalizing on the impressive capabilities of large language models (LLMs) across diverse tasks. Despite this, a critical challenge known as hallucination occurs when…

Computer Vision and Pattern Recognition · Computer Science 2025-03-07 Chao Wang , Weiwei Fu , Yang Zhou

Reinforcement learning (RL) is a critical component of large language model (LLM) post-training. However, on-policy algorithms used for post-training are not naturally robust to a diversified content of experience replay buffers, which…

Continual Learning (CL) is an emerging machine learning paradigm that aims to learn from a continuous stream of tasks without forgetting knowledge learned from the previous tasks. To avoid performance decrease caused by forgetting, prior…

Machine Learning · Computer Science 2023-01-02 Soobee Lee , Minindu Weerakoon , Jonghyun Choi , Minjia Zhang , Di Wang , Myeongjae Jeon

Large language models (LLMs) and multimodal models (MMs) have exhibited impressive capabilities in various domains, particularly in general language understanding and visual reasoning. However, these models, trained on massive data, may not…

Computation and Language · Computer Science 2024-12-19 Xinbo Wu , Max Hartman , Vidhata Arjun Jayaraman , Lav R. Varshney

As language models continue to rapidly improve, we can expect their actions and reasoning to become difficult or impossible for weaker agents and humans to follow, undermining interpretability and oversight. With an eye on long-term…

Artificial Intelligence · Computer Science 2026-01-27 Robert West , Ashton Anderson , Ece Kamar , Eric Horvitz

Recent advances in natural language processing highlight two key factors for improving reasoning in large language models (LLMs): (i) allocating more test-time compute tends to help on harder problems but often introduces redundancy in the…

Computation and Language · Computer Science 2025-11-04 Riccardo Alberghi , Elizaveta Demyanenko , Luca Biggio , Luca Saglietti

Despite remarkable successes achieved by modern neural networks in a wide range of applications, these networks perform best in domain-specific stationary environments where they are trained only once on large-scale controlled data…

Neural and Evolutionary Computing · Computer Science 2019-04-23 Pouya Bashivan , Martin Schrimpf , Robert Ajemian , Irina Rish , Matthew Riemer , Yuhai Tu

Recurrent neural networks have been very successful at predicting sequences of words in tasks such as language modeling. However, all such models are based on the conventional classification framework, where the model is trained against…

Machine Learning · Computer Science 2017-03-14 Hakan Inan , Khashayar Khosravi , Richard Socher

Continual Learning is considered a key step toward next-generation Artificial Intelligence. Among various methods, replay-based approaches that maintain and replay a small episodic memory of previous samples are one of the most successful…

Machine Learning · Computer Science 2022-12-27 Guangji Bai , Chen Ling , Yuyang Gao , Liang Zhao

Artificial neural networks suffer from catastrophic forgetting when they are sequentially trained on multiple tasks. To overcome this problem, we present a novel approach based on task-conditioned hypernetworks, i.e., networks that generate…

Machine Learning · Computer Science 2022-04-12 Johannes von Oswald , Christian Henning , Benjamin F. Grewe , João Sacramento

Large Reasoning Models (LRMs) often suffer from the ``over-thinking'' problem, generating unnecessarily long reasoning on simple tasks. Some strategies have been proposed to mitigate this issue, such as length penalties or routing…

Computation and Language · Computer Science 2025-10-16 Jian Xie , Zhendong Chu , Aoxiao Zhong , Kai Zhang , Mingzhe Han , Xing Fan , Jialie Shen , Qingsong Wen

Lifelong learning is a very important step toward realizing robust autonomous artificial agents. Neural networks are the main engine of deep learning, which is the current state-of-the-art technique in formulating adaptive artificial…

Machine Learning · Computer Science 2019-12-11 Mohammed Amer , Tomás Maul

Large language models (LLMs) excel at single-turn reasoning but often lose accuracy and coherence over extended, multi-turn interactions. Recent evaluations such as TurnBench highlight recurring failure modes-reasoning bias, task drift,…

Computation and Language · Computer Science 2025-12-17 Yiran Zhang , Jincheng Hu , Mark Dras , Usman Naseem

Most research on lifelong learning applies to images or games, but not language. We present LAMOL, a simple yet effective method for lifelong language learning (LLL) based on language modeling. LAMOL replays pseudo-samples of previous tasks…

Computation and Language · Computer Science 2019-12-24 Fan-Keng Sun , Cheng-Hao Ho , Hung-Yi Lee

Large Language Models (LLMs) have become a mainstay for many everyday applications. However, as data evolve their knowledge quickly becomes outdated. Continual learning aims to update LLMs with new information without erasing previously…

Machine Learning · Computer Science 2026-01-05 Thomas Katraouras , Dimitrios Rafailidis

Tangent Model Composition (TMC) is a method to combine component models independently fine-tuned around a pre-trained point. Component models are tangent vectors to the pre-trained model that can be added, scaled, or subtracted to support…

Machine Learning · Computer Science 2023-10-03 Tian Yu Liu , Stefano Soatto

Large language models (LLMs) have rapidly progressed into general-purpose agents capable of solving a broad spectrum of tasks. However, current models remain inefficient at reasoning: they apply fixed inference-time compute regardless of…

Modern large language models (LLMs) excel at tasks that require storing and retrieving knowledge, such as factual recall and question answering. Transformers are central to this capability because they can encode information during training…

Machine Learning · Statistics 2026-03-18 Nuri Mert Vural , Alberto Bietti , Mahdi Soltanolkotabi , Denny Wu

Predictive Coding (PC) is a biologically-inspired learning framework characterised by local, parallelisable operations, properties that enable energy-efficient implementation on neuromorphic hardware. Despite this, extending PC effectively…

Machine Learning · Computer Science 2026-02-23 Tom Potter , Oliver Rhodes