English
Related papers

Related papers: FlyPrompt: Brain-Inspired Random-Expanded Routing …

200 papers

Continual Learning (CL) aims to incrementally update a trained model on new tasks without forgetting the acquired knowledge of old ones. Existing CL methods usually reduce forgetting with task priors, \ie using task identity or a subset of…

Computer Vision and Pattern Recognition · Computer Science 2023-10-17 Tao Zhuo , Zhiyong Cheng , Hehe Fan , Mohan Kankanhalli

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

Preference alignment has enabled large language models (LLMs) to better reflect human expectations, but current methods mostly optimize for population-level preferences, overlooking individual users. Personalization is essential, yet early…

Computation and Language · Computer Science 2026-03-06 Chengbing Wang , Yang Zhang , Wenjie Wang , Xiaoyan Zhao , Fuli Feng , Xiangnan He , Tat-Seng Chua

Graph neural networks stand as the predominant technique for graph representation learning owing to their strong expressive power, yet the performance highly depends on the availability of high-quality labels in an end-to-end manner. Thus…

Machine Learning · Computer Science 2024-11-27 Jiazheng Li , Jundong Li , Chuxu Zhang

The emergence of large language models (LLMs) like GPT-4 has revolutionized natural language processing (NLP), enabling diverse, complex tasks. However, extensive token counts lead to high computational and financial burdens. To address…

Computation and Language · Computer Science 2025-03-12 Yun-Hao Cao , Yangsong Wang , Shuzheng Hao , Zhenxing Li , Chengjun Zhan , Sichao Liu , Yi-Qi Hu

Test-time scaling improves LLM performance by generating multiple candidate solutions, yet token-level sampling requires temperature tuning that trades off diversity against stability. Fine-grained MoE, featuring hundreds of well-trained…

Machine Learning · Computer Science 2026-05-04 Yuanteng Chen , Peisong Wang , Nanxin Zeng , Yuantian Shao , Shuang Qiu , Gang Li , Jing Liu , Jian Cheng

Continual learning (CL) is a new online learning technique over sequentially generated streaming data from different tasks, aiming to maintain a small forgetting loss on previously-learned tasks. Existing work focuses on reducing the…

Machine Learning · Computer Science 2024-12-25 Shugang Hao , Lingjie Duan

A common challenge in continual learning (CL) is catastrophic forgetting, where the performance on old tasks drops after new, additional tasks are learned. In this paper, we propose a novel framework called ReCL to slow down forgetting in…

Machine Learning · Computer Science 2025-03-04 Pascal Janetzky , Tobias Schlagenhauf , Stefan Feuerriegel

Prompt-Tuning is a new paradigm for finetuning pre-trained language models in a parameter-efficient way. Here, we explore the use of HyperNetworks to generate hyper-prompts: we propose HyperPrompt, a novel architecture for prompt-based…

Computation and Language · Computer Science 2022-06-16 Yun He , Huaixiu Steven Zheng , Yi Tay , Jai Gupta , Yu Du , Vamsi Aribandi , Zhe Zhao , YaGuang Li , Zhao Chen , Donald Metzler , Heng-Tze Cheng , Ed H. Chi

Managing evolving graph data presents substantial challenges in storage and privacy, and training graph neural networks (GNNs) on such data often leads to catastrophic forgetting, impairing performance on earlier tasks. Despite existing…

Machine Learning · Computer Science 2025-05-29 Yinlin Zhu , Miao Hu , Di Wu

Large pre-trained models have exhibited remarkable achievements across various domains. The substantial training costs associated with these models have led to wide studies of fine-tuning for effectively harnessing their capabilities in…

Machine Learning · Computer Science 2024-07-26 Linxiao Cao , Yifei Zhu , Wei Gong

Online continual learning (CL) studies the problem of learning continuously from a single-pass data stream while adapting to new data and mitigating catastrophic forgetting. Recently, by storing a small subset of old data, replay-based…

Computer Vision and Pattern Recognition · Computer Science 2023-08-02 Yujie Wei , Jiaxin Ye , Zhizhong Huang , Junping Zhang , Hongming Shan

Class Incremental Learning (CIL) based on pre-trained models offers a promising direction for open-world continual learning. Existing methods typically rely on correlation-based strategies, where an image's classification feature is used as…

Computer Vision and Pattern Recognition · Computer Science 2025-05-20 Libo Huang , Zhulin An , Chuanguang Yang , Boyu Diao , Fei Wang , Yan Zeng , Zhifeng Hao , Yongjun Xu

We introduce Prompt Curriculum Learning (PCL), a lightweight reinforcement learning (RL) algorithm that selects intermediate-difficulty prompts using a learned value model to post-train language models. Since post-training LLMs via RL…

Machine Learning · Computer Science 2025-10-02 Zhaolin Gao , Joongwon Kim , Wen Sun , Thorsten Joachims , Sid Wang , Richard Yuanzhe Pang , Liang Tan

Continual learning (CL) aims to incrementally learn different tasks (such as classification) in a non-stationary data stream without forgetting old ones. Most CL works focus on tackling catastrophic forgetting under a learning-from-scratch…

Machine Learning · Computer Science 2024-01-17 Mark D. McDonnell , Dong Gong , Amin Parveneh , Ehsan Abbasnejad , Anton van den Hengel

Continual learning (CL) on edge devices requires not only high accuracy but also training-time efficiency to support on-device adaptation under strict memory and computational constraints. While prompt-based continual learning (PCL) is…

Machine Learning · Computer Science 2026-04-10 Wonseon Lim , Jaesung Lee , Dae-Won Kim

As a novel approach to tuning pre-trained models, prompt tuning involves freezing the parameters in downstream tasks while inserting trainable embeddings into inputs in the first layer. However, previous methods have mainly focused on the…

Computation and Language · Computer Science 2023-05-16 Chi Liu , Haochun Wang , Nuwa Xi , Sendong Zhao , Bing Qin

Federated Class Continual Learning (FCCL) merges the challenges of distributed client learning with the need for seamless adaptation to new classes without forgetting old ones. The key challenge in FCCL is catastrophic forgetting, an issue…

Machine Learning · Computer Science 2024-09-05 Jinglin Liang , Jin Zhong , Hanlin Gu , Zhongqi Lu , Xingxing Tang , Gang Dai , Shuangping Huang , Lixin Fan , Qiang Yang

Continual learning (CL) learns a sequence of tasks incrementally with the goal of achieving two main objectives: overcoming catastrophic forgetting (CF) and encouraging knowledge transfer (KT) across tasks. However, most existing techniques…

Computation and Language · Computer Science 2021-12-21 Zixuan Ke , Bing Liu , Nianzu Ma , Hu Xu , Lei Shu

In-context learning (ICL) derives its power from enabling Large Language Models to adapt to new tasks via prompt-based reasoning alone, entirely bypassing the need for parameter updates. Existing theories primarily study ICL in single-task…

Machine Learning · Computer Science 2026-05-28 Guangyu Li , Meng Ding , Lijie Hu
‹ Prev 1 3 4 5 6 7 10 Next ›