English
Related papers

Related papers: Merge before Forget: A Single LoRA Continual Learn…

200 papers

In neural networks, continual learning results in gradient interference among sequential tasks, leading to catastrophic forgetting of old tasks while learning new ones. This issue is addressed in recent methods by storing the important…

Machine Learning · Computer Science 2023-02-06 Gobinda Saha , Kaushik Roy

Catastrophic forgetting remains a critical challenge in continual learning for large language models (LLMs), where models struggle to retain performance on historical tasks when fine-tuning on new sequential data without access to past…

Machine Learning · Computer Science 2025-09-30 Zhixin Zhang , Zeming Wei , Meng Sun

In continual learning (CL), a learner is faced with a sequence of tasks, arriving one after the other, and the goal is to remember all the tasks once the continual learning experience is finished. The prior art in CL uses episodic memory,…

Machine Learning · Computer Science 2020-12-09 Arslan Chaudhry , Naeemullah Khan , Puneet K. Dokania , Philip H. S. Torr

Large Language Models (LLMs) must continuously learn and update knowledge to remain effective in dynamic real-world environments. While Low-Rank Adaptation (LoRA) is widely used for such memory updates, existing studies mainly rely on…

Computation and Language · Computer Science 2026-05-29 Ziwen Xu , Haiwen Hong , Linsong Yu , Benglei Cui , Longtao Huang , Hui Xue , Ningyu Zhang

In this paper, we focus on a long-term continual learning (CL) task, where a model learns sequentially from a stream of vast tasks over time, acquiring new knowledge while retaining previously learned information in a manner akin to human…

Machine Learning · Computer Science 2025-05-16 Tianyu Huai , Jie Zhou , Yuxuan Cai , Qin Chen , Wen Wu , Xingjiao Wu , Xipeng Qiu , Liang He

Large Language Models (LLMs) suffer severe catastrophic forgetting when adapted sequentially to new tasks in a continual learning (CL) setting. Existing approaches are fundamentally limited: replay-based methods are impractical and…

Machine Learning · Computer Science 2026-01-08 Shristi Das Biswas , Yue Zhang , Anwesan Pal , Radhika Bhargava , Kaushik Roy

The performance of Large Language Models (LLMs) on many tasks is greatly limited by the knowledge learned during pre-training and stored in the model's parameters. Low-rank adaptation (LoRA) is a popular and efficient training technique for…

Computation and Language · Computer Science 2025-03-25 Sergey Pletenev , Maria Marina , Daniil Moskovskiy , Vasily Konovalov , Pavel Braslavski , Alexander Panchenko , Mikhail Salnikov

Low-rank Adaptation (LoRA) has gained popularity as a fine-tuning approach for Large Language Models (LLMs) due to its low resource requirements and good performance. While a plethora of work has investigated improving LoRA serving…

Machine Learning · Computer Science 2025-08-06 Minghao Yan , Zhuang Wang , Zhen Jia , Shivaram Venkataraman , Yida Wang

Pre-trained language models (PLMs) demonstrate remarkable intelligence but struggle with emerging tasks unseen during training in real-world applications. Training separate models for each new task is usually impractical. Multi-task…

Computation and Language · Computer Science 2025-05-02 Xiao Zhang , Kangsheng Wang , Tianyu Hu , Huimin Ma

Continual learning (CL) aims to continually accumulate knowledge from a non-stationary data stream without catastrophic forgetting of learned knowledge, requiring a balance between stability and adaptability. Relying on the generalizable…

Machine Learning · Computer Science 2025-03-28 Huiyi Wang , Haodong Lu , Lina Yao , Dong Gong

Food analysis has become increasingly critical for health-related tasks such as personalized nutrition and chronic disease prevention. However, existing large multimodal models (LMMs) in food analysis suffer from catastrophic forgetting…

Machine Learning · Computer Science 2025-11-18 Xinlan Wu , Bin Zhu , Feng Han , Pengkun Jiao , Jingjing Chen

Fueled by their remarkable ability to tackle diverse tasks across multiple domains, large language models (LLMs) have grown at an unprecedented rate, with some recent models containing trillions of parameters. This growth is accompanied by…

Machine Learning · Computer Science 2025-05-30 Athanasios Glentis , Jiaxiang Li , Qiulin Shang , Andi Han , Ioannis Tsaknakis , Quan Wei , Mingyi Hong

LoRA employs lightweight modules to customize large language models (LLMs) for each downstream task or domain, where different learned additional modules represent diverse skills. Combining existing LoRAs to address new tasks can enhance…

Computation and Language · Computer Science 2024-02-20 Hanqing Wang , Bowen Ping , Shuo Wang , Xu Han , Yun Chen , Zhiyuan Liu , Maosong Sun

Federated learning (FL) is a popular paradigm for collaborative training which avoids direct data exposure between clients. However, data privacy issues still remain: FL-trained large language models are capable of memorizing and completing…

Machine Learning · Computer Science 2026-03-10 Thierry Bossy , Julien Vignoud , Tahseen Rabbani , Juan R. Troncoso Pastoriza , Martin Jaggi

Training large language models (LLMs) typically involves pre-training on massive corpora, only to restart the process entirely when new data becomes available. A more efficient and resource-conserving approach would be continual…

Low-Rank Adaptation (LoRA) has become one of the most widely used fine-tuning mechanisms for adapting large language models to new domains, tasks, and users. Yet adaptation performance alone can obscure an important failure mode: LoRA…

Computation and Language · Computer Science 2026-05-29 Runze Xu , Arpit Garg , Hemanth Saratchandran , Simon Lucey

Large language models (LLMs) increasingly require mechanisms for continual adaptation without full retraining. However, sequential updates can lead to catastrophic forgetting, where new edits degrade previously acquired knowledge. This work…

Machine Learning · Computer Science 2025-10-21 William Hoy , Nurcin Celik

Deep model merging represents an emerging research direction that combines multiple fine-tuned models to harness their specialized capabilities across different tasks and domains. Current model merging techniques focus on merging all…

Machine Learning · Computer Science 2025-01-17 Anke Tang , Enneng Yang , Li Shen , Yong Luo , Han Hu , Bo Du , Dacheng Tao

With more open-source models available for diverse tasks, model merging has gained attention by combining models into one, reducing training, storage, and inference costs. Current research mainly focuses on model merging for full…

Computer Vision and Pattern Recognition · Computer Science 2025-05-23 Shenghe Zheng , Hongzhi Wang , Chenyu Huang , Xiaohui Wang , Tao Chen , Jiayuan Fan , Shuyue Hu , Peng Ye

Foundation models update slowly due to resource-intensive training, whereas domain-specific models evolve rapidly between releases. Model merging seeks to combine multiple expert models into a single, more capable model, reducing storage…

Artificial Intelligence · Computer Science 2026-03-04 Yongxian Wei , Runxi Cheng , Weike Jin , Enneng Yang , Li Shen , Lu Hou , Sinan Du , Chun Yuan , Xiaochun Cao , Dacheng Tao