English
Related papers

Related papers: Lifelong Learning with Task-Specific Adaptation: A…

200 papers

Lifelong learning is critical for embodied agents in open-world environments, where reinforcement learning fine-tuning has emerged as an important paradigm to enable Vision-Language-Action (VLA) models to master dexterous manipulation…

Artificial Intelligence · Computer Science 2026-02-04 Qixin Zeng , Shuo Zhang , Hongyin Zhang , Renjie Wang , Han Zhao , Libang Zhao , Runze Li , Donglin Wang , Chao Huang

Lifelong Reinforcement Learning (LRL) holds significant potential for addressing sequential tasks, but it still faces considerable challenges. A key difficulty lies in effectively preventing catastrophic forgetting and facilitating…

Machine Learning · Computer Science 2025-03-18 Zhiyi Huang , Xiaohan Shan , Jianmin Li

Recent works on parameter-efficient transfer learning (PETL) show the potential to adapt a pre-trained Vision Transformer to downstream recognition tasks with only a few learnable parameters. However, since they usually insert new…

Computer Vision and Pattern Recognition · Computer Science 2024-07-16 Taolin Zhang , Jiawang Bai , Zhihe Lu , Dongze Lian , Genping Wang , Xinchao Wang , Shu-Tao Xia

World model based reinforcement learning (RL) has emerged as a promising approach for autonomous driving, which learns a latent dynamics model and uses it to train a planning policy. To speed up the learning process, the pretrain-finetune…

Robotics · Computer Science 2025-01-24 Hang Wang , Xin Ye , Feng Tao , Chenbin Pan , Abhirup Mallik , Burhaneddin Yaman , Liu Ren , Junshan Zhang

Navigating multiple tasks$\unicode{x2014}$for instance in succession as in continual or lifelong learning, or in distributions as in meta or multi-task learning$\unicode{x2014}$requires some notion of adaptation. Evolution over timescales…

Machine Learning · Computer Science 2024-11-20 Sebastian Lee , Samuel Liebana , Claudia Clopath , Will Dabney

Activation steering has emerged as a promising approach for efficiently adapting large language models (LLMs) to downstream behaviors. However, most existing steering methods rely on a single static direction per task or concept, making…

Reinforcement learning (RL) faces substantial challenges when applied to real-life problems, primarily stemming from the scarcity of available data due to limited interactions with the environment. This limitation is exacerbated by the fact…

Neural and Evolutionary Computing · Computer Science 2024-04-10 Cristiano Capone , Paolo Muratore

Continual learning (CL) enables models to adapt to evolving data streams. A major challenge of CL is catastrophic forgetting, where new knowledge will overwrite previously acquired knowledge. Traditional methods usually retain the past data…

Computer Vision and Pattern Recognition · Computer Science 2025-07-04 Baocai Yin , Ji Zhao , Huajie Jiang , Ningning Hou , Yongli Hu , Amin Beheshti , Ming-Hsuan Yang , Yuankai Qi

Federated Parameter-Efficient Fine-Tuning (Fed-PEFT) enables lightweight adaptation of large pre-trained models in federated learning settings by updating only a small subset of parameters. However, Fed-PEFT methods typically assume a fixed…

Machine Learning · Computer Science 2026-04-13 Feng Yu , Jia Hu , Geyong Min

Continual learning (CL) is essential for Large Language Models (LLMs) to adapt to evolving real-world demands, yet they are susceptible to catastrophic forgetting (CF). While traditional CF solutions rely on expensive data rehearsal, recent…

Machine Learning · Computer Science 2025-02-18 Huanxuan Liao , Shizhu He , Yupu Hao , Jun Zhao , Kang Liu

Alignment plays a crucial role in Large Language Models (LLMs) in aligning with human preferences on a specific task/domain. Traditional alignment methods suffer from catastrophic forgetting, where models lose previously acquired knowledge…

Computation and Language · Computer Science 2026-04-09 Junsong Li , Jie Zhou , Bihao Zhan , Yutao Yang , Qianjun Pan , Shilian Chen , Tianyu Huai , Xin Li , Qin Chen , Liang He

To cope with real-world dynamics, an intelligent system needs to incrementally acquire, update, accumulate, and exploit knowledge throughout its lifetime. This ability, known as continual learning, provides a foundation for AI systems to…

Machine Learning · Computer Science 2024-02-07 Liyuan Wang , Xingxing Zhang , Hang Su , Jun Zhu

Linear attention offers a linear-time alternative to self-attention but often struggles to capture long-range patterns. We revisit linear attention through a prediction-correction lens and show that prevalent variants can be written as a…

Machine Learning · Computer Science 2025-10-01 Xunhao Lai , Jialiang Kang , Jianqiao Lu , Tong Lin , Pengyu Zhao

This paper introduces a new lifelong learning solution where a single model is trained for a sequence of tasks. The main challenge that vision systems face in this context is catastrophic forgetting: as they tend to adapt to the most…

Computer Vision and Pattern Recognition · Computer Science 2018-07-19 Amal Rannen Triki , Rahaf Aljundi , Mathew B. Blaschko , Tinne Tuytelaars

Intelligent agents should have the ability to leverage knowledge from previously learned tasks in order to learn new ones quickly and efficiently. Meta-learning approaches have emerged as a popular solution to achieve this. However,…

Machine Learning · Computer Science 2023-02-17 Zhao Mandi , Pieter Abbeel , Stephen James

Adversarial attacks pose a significant threat to the reliability of pre-trained language models (PLMs) such as GPT, BERT, RoBERTa, and T5. This paper presents Adversarial Robustness through Dynamic Ensemble Learning (ARDEL), a novel scheme…

Cryptography and Security · Computer Science 2025-05-14 Hetvi Waghela , Jaydip Sen , Sneha Rakshit

While vision-and-language models significantly advance in many fields, the challenge of continual learning is unsolved. Parameter-efficient modules like adapters and prompts present a promising way to alleviate catastrophic forgetting.…

Machine Learning · Computer Science 2024-10-16 Hong Li , Zhiquan Tan , Xingyu Li , Weiran Huang

The pretrain-then-finetune paradigm has been widely used in various unimodal and multimodal tasks. However, finetuning all the parameters of a pre-trained model becomes prohibitive as the model size grows exponentially. To address this…

Multimedia · Computer Science 2023-08-29 Hongye Liu , Xianhai Xie , Yang Gao , Size Li , Zhou YU

Continual learning (CL) has emerged as a pivotal paradigm to enable large language models (LLMs) to dynamically adapt to evolving knowledge and sequential tasks while mitigating catastrophic forgetting-a critical limitation of the static…

Computation and Language · Computer Science 2026-03-16 Hongyang Chen , Zhongwu Sun , Hongfei Ye , Kunchi Li , Xuemin Lin

This paper addresses the issues of parameter redundancy, rigid structure, and limited task adaptability in the fine-tuning of large language models. It proposes an adapter-based fine-tuning method built on a structure-learnable mechanism.…

Computation and Language · Computer Science 2025-09-04 Ming Gong , Yingnan Deng , Nia Qi , Yujun Zou , Zhihao Xue , Yun Zi