English
Related papers

Related papers: AIMMerging: Adaptive Iterative Model Merging Using…

200 papers

The escalating scale of Large Language Models (LLMs) necessitates efficient adaptation techniques. Model merging has gained prominence for its efficiency and controllability. However, existing merging techniques typically serve as post-hoc…

The recent success of large language models (LLMs) trained on static, pre-collected, general datasets has sparked numerous research directions and applications. One such direction addresses the non-trivial challenge of integrating…

Machine Learning · Computer Science 2024-11-26 Haizhou Shi , Zihao Xu , Hengyi Wang , Weiyi Qin , Wenyuan Wang , Yibin Wang , Zifeng Wang , Sayna Ebrahimi , Hao Wang

Learning a set of tasks over time, also known as continual learning (CL), is one of the most challenging problems in artificial intelligence due to catastrophic forgetting. Large language models (LLMs) are often impractical to frequent…

Machine Learning · Computer Science 2025-10-28 Jaya Krishna Mandivarapu

Generative large language models (LLMs) exhibit impressive capabilities, which can be further augmented by integrating a pre-trained vision model into the original LLM to create a multimodal LLM (MLLM). However, this integration often…

Computation and Language · Computer Science 2025-08-14 Shikhar Srivastava , Md Yousuf Harun , Robik Shrestha , Christopher Kanan

Continued pretraining (CPT) is a popular approach to adapt existing large language models (LLMs) to new languages. When doing so, it is common practice to include a portion of English data in the mixture, but its role has not been carefully…

Computation and Language · Computer Science 2025-09-22 Ahmed Elhady , Eneko Agirre , Mikel Artetxe

Large language models (LLMs) are not amenable to frequent re-training, due to high training costs arising from their massive scale. However, updates are necessary to endow LLMs with new skills and keep them up-to-date with rapidly evolving…

Computation and Language · Computer Science 2024-02-08 Tongtong Wu , Linhao Luo , Yuan-Fang Li , Shirui Pan , Thuy-Trang Vu , Gholamreza Haffari

Although multimodal large language models (MLLMs) have achieved impressive performance, the multimodal instruction tuning stage often causes catastrophic forgetting of the base LLM's language ability, even in strong models like Llama3. To…

Computation and Language · Computer Science 2025-05-23 Zeping Yu , Sophia Ananiadou

Large language models (LLMs) can adapt to new tasks via in-context learning (ICL) without parameter updates, making them powerful learning engines for fast adaptation. While extensive research has examined ICL as a few-shot learner, whether…

Machine Learning · Computer Science 2025-09-30 Liuwang Kang , Fan Wang , Shaoshan Liu , Hung-Chyun Chou , Chuan Lin , Ning Ding

Optimizing data mixtures is essential for unlocking the full potential of large language models (LLMs), yet identifying the optimal composition remains computationally prohibitive due to reliance on heuristic trials or expensive proxy…

Machine Learning · Computer Science 2026-01-27 Jiapeng Wang , Changxin Tian , Kunlong Chen , Ziqi Liu , Jiaxin Mao , Wayne Xin Zhao , Zhiqiang Zhang , Jun Zhou

Continual learning (CL) for large language models (LLMs) aims to enable sequential knowledge acquisition without catastrophic forgetting. Memory replay methods are widely used for their practicality and effectiveness, but most rely on…

Machine Learning · Computer Science 2026-04-21 Yujie Feng , Hao Wang , Jian Li , Xu Chu , Zhaolu Kang , Yiran Liu , Yasha Wang , Philip S. Yu , Xiao-Ming Wu

Continual instruction tuning enables large language models (LLMs) to learn incrementally while retaining past knowledge, whereas existing methods primarily focus on how to retain old knowledge rather than on selecting which new knowledge to…

Computation and Language · Computer Science 2025-03-21 Peiyi Lin , Fukai Zhang , Kai Niu , Hao Fu

Class-incremental Learning (CIL) enables the model to incrementally absorb knowledge from new classes and build a generic classifier across all previously encountered classes. When the model optimizes with new classes, the knowledge of…

Computer Vision and Pattern Recognition · Computer Science 2025-03-31 Juncen Guo , Xiaoguang Zhu , Liangyu Teng , Hao Yang , Jing Liu , Yang Liu , Liang Song

Retrieval-Augmented Generation (RAG) systems leverage Large Language Models (LLMs) to generate accurate and reliable responses that are grounded in retrieved context. However, LLMs often generate inconsistent outputs for semantically…

Computation and Language · Computer Science 2025-10-17 Xujun Peng , Anoop Kumar , Jingyu Wu , Parker Glenn , Daben Liu

This article develops iterative machine learning (IML) for output tracking. The input-output data generated during iterations to develop the model used in the iterative update. The main contribution of this article to propose the use of…

Systems and Control · Computer Science 2018-01-04 Santosh Devasia

Developing autonomous vehicles (AVs) helps improve the road safety and traffic efficiency of intelligent transportation systems (ITS). Accurately predicting the trajectories of traffic participants is essential to the decision-making and…

Robotics · Computer Science 2022-12-22 Yunlong Lin , Zirui Li , Cheng Gong , Chao Lu , Xinwei Wang , Jianwei Gong

Large language models (LLMs) can acquire new capabilities through fine-tuning, but continual adaptation often leads to catastrophic forgetting. We propose CRAFT, a continual learning framework that avoids updating model weights by instead…

Machine Learning · Computer Science 2026-05-11 Md Anwar Hossen , Fatema Siddika , Juan Pablo Munoz , Tanya Roosta , Ali Jannesari

Large language models (LLMs) have enabled the creation of multi-modal LLMs that exhibit strong comprehension of visual data such as images and videos. However, these models usually rely on extensive visual tokens from visual encoders,…

Computer Vision and Pattern Recognition · Computer Science 2025-07-30 Yiwu Zhong , Zhuoming Liu , Yin Li , Liwei Wang

Catastrophic forgetting, the tendency of neural networks to forget previously learned knowledge when learning new tasks, has been a major challenge in continual learning (CL). To tackle this challenge, CL methods have been proposed and…

Machine Learning · Computer Science 2026-03-04 Zhanwang Liu , Yuting Li , Haoyuan Gao , Yexin Li , Linghe Kong , Lichao Sun , Weiran Huang

Continual Learning (CL) focuses on learning from dynamic and changing data distributions while retaining previously acquired knowledge. Various methods have been developed to address the challenge of catastrophic forgetting, including…

Machine Learning · Computer Science 2024-03-21 Zhenyi Wang , Yan Li , Li Shen , Heng Huang

Continual learning (CL) refers to the ability to continually learn over time by accommodating new knowledge while retaining previously learned experience. While this concept is inherent in human learning, current machine learning methods…

Machine Learning · Computer Science 2024-08-15 Anna Vettoruzzo , Joaquin Vanschoren , Mohamed-Rafik Bouguelia , Thorsteinn Rögnvaldsson