English
Related papers

Related papers: Componential Prompt-Knowledge Alignment for Domain…

200 papers

Prompt-based continual learning methods fine-tune only a small set of additional learnable parameters while keeping the pre-trained model's parameters frozen. It enables efficient adaptation to new tasks while mitigating the risk of…

Computer Vision and Pattern Recognition · Computer Science 2026-05-11 Shengqin Jiang , Tianqi Kong , Yuankai Qi , Haokui Zhang , Lina Yao , Quan Z. Sheng , Qingshan Liu , Ming-Hsuan Yang

Incremental learning (IL) aims to overcome catastrophic forgetting of previous tasks while learning new ones. Existing IL methods make strong assumptions that the incoming task type will either only increases new classes or domains (i.e.…

Computer Vision and Pattern Recognition · Computer Science 2025-05-21 Sheng Luo , Yi Zhou , Tao Zhou

Despite significant progress and advances in autonomous driving, many end-to-end systems still struggle with domain adaptation (DA), such as transferring a policy trained under clear weather to adverse weather conditions. Typical DA…

Robotics · Computer Science 2025-11-18 Aleesha Khurram , Amir Moeini , Shangtong Zhang , Rohan Chandra

Deep Learning (DL) models proved themselves to perform extremely well on a wide variety of learning tasks, as they can learn useful patterns from large data sets. However, purely data-driven models might struggle when very difficult…

Machine Learning · Computer Science 2020-05-22 Andrea Borghesi , Federico Baldo , Michela Milano

Continual pretraining promises to adapt large language models (LLMs) to new domains using only unlabeled test-time data, but naively applying standard self-supervised objectives to instruction-tuned models is known to degrade their…

Artificial Intelligence · Computer Science 2025-10-24 Tianyi Zhang , Florian Mai , Lucie Flek

Knowledge distillation (KD) is an effective model compression method that can transfer the internal capabilities of large language models (LLMs) to smaller ones. However, the multi-modal probability distribution predicted by teacher LLMs…

Computation and Language · Computer Science 2024-12-19 Tianyu Peng , Jiajun Zhang

With numerous medical tasks, the performance of deep models has recently experienced considerable improvements. These models are often adept learners. Yet, their intricate architectural design and high computational complexity make…

Image and Video Processing · Electrical Eng. & Systems 2023-03-17 Eddardaa Ben Loussaief , Hatem Rashwan , Mohammed Ayad , Mohammed Zakaria Hassan , Domenec Puig

Knowledge distillation (KD) is an efficient framework for compressing large-scale pre-trained language models. Recent years have seen a surge of research aiming to improve KD by leveraging Contrastive Learning, Intermediate Layer…

Computation and Language · Computer Science 2022-04-19 Md Akmal Haidar , Mehdi Rezagholizadeh , Abbas Ghaddar , Khalil Bibi , Philippe Langlais , Pascal Poupart

Knowledge distillation (KD) is widely used for compressing a teacher model to a smaller student model, reducing its inference cost and memory footprint while preserving model capabilities. However, current KD methods for auto-regressive…

Computation and Language · Computer Science 2024-07-04 Jongwoo Ko , Sungnyun Kim , Tianyi Chen , Se-Young Yun

When learning new tasks in a sequential manner, deep neural networks tend to forget tasks that they previously learned, a phenomenon called catastrophic forgetting. Class incremental learning methods aim to address this problem by keeping a…

Machine Learning · Computer Science 2022-06-20 Jinlin Xiang , Eli Shlizerman

Knowledge distillation (KD) has proven highly effective for compressing large models and enhancing the performance of smaller ones. However, its effectiveness diminishes in cross-modal scenarios, such as vision-to-language distillation,…

Computer Vision and Pattern Recognition · Computer Science 2025-11-26 Junhong Liu , Yuan Zhang , Tao Huang , Wenchao Xu , Renyu Yang

With the advancement of large pre-trained vision-language models, effectively transferring the knowledge embedded within these foundational models to downstream tasks has become a pivotal topic, particularly in data-scarce environments.…

Computer Vision and Pattern Recognition · Computer Science 2024-09-12 Tianxiang Hao , Mengyao Lyu , Hui Chen , Sicheng Zhao , Xiaohan Ding , Jungong Han , Guiguang Ding

In the realm of class-incremental learning (CIL), alleviating the catastrophic forgetting problem is a pivotal challenge. This paper discovers a counter-intuitive observation: by incorporating domain shift into CIL tasks, the forgetting…

Computer Vision and Pattern Recognition · Computer Science 2025-01-03 Wei Chen , Yi Zhou

Large language models (LLMs) have significantly advanced various natural language processing tasks, but deploying them remains computationally expensive. Knowledge distillation (KD) is a promising solution, enabling the transfer of…

Computation and Language · Computer Science 2024-10-22 Yuhang Zhou , Jing Zhu , Paiheng Xu , Xiaoyu Liu , Xiyao Wang , Danai Koutra , Wei Ai , Furong Huang

Class incremental learning(CIL) has attracted much attention, but most existing related works focus on fine-tuning the entire representation model, which inevitably results in much catastrophic forgetting. In the contrast, with a…

Computer Vision and Pattern Recognition · Computer Science 2023-02-10 Jieren Deng , Jianhua Hu , Haojian Zhang , Yunkuan Wang

While deep learning models excel at predictive tasks, they often overfit due to their complex structure and large number of parameters, causing them to memorize training data, including noise, rather than learn patterns that generalize to…

Machine Learning · Computer Science 2025-09-29 Joshua Salim , Jordan Yu , Xilei Zhao

Online Class-Incremental continual Learning (OCIL) addresses the challenge of continuously learning from a single-channel data stream, adapting to new tasks while mitigating catastrophic forgetting. Recently, Mutual Information (MI)-based…

Machine Learning · Computer Science 2024-07-29 Huan Zhang , Fan Lyu , Shenghua Fan , Yujin Zheng , Dingwen Wang

Pre-trained vision-language (V-L) models such as CLIP have shown excellent generalization ability to downstream tasks. However, they are sensitive to the choice of input text prompts and require careful selection of prompt templates to…

Computer Vision and Pattern Recognition · Computer Science 2023-04-04 Muhammad Uzair Khattak , Hanoona Rasheed , Muhammad Maaz , Salman Khan , Fahad Shahbaz Khan

Large language models (LLMs) are commonly trained on multi-domain datasets, where domain sampling strategies significantly impact model performance due to varying domain importance across downstream tasks. Existing approaches for optimizing…

Computation and Language · Computer Science 2025-08-25 Weijie Shi , Jipeng Zhang , Yaguang Wu , Jingzhi Fang , Ruiyuan Zhang , Jiajie Xu , Jia Zhu , Hao Chen , Yao Zhao , Sirui Han , Xiaofang Zhou

Recent advances in decentralized deep learning algorithms have demonstrated cutting-edge performance on various tasks with large pre-trained models. However, a pivotal prerequisite for achieving this level of competitiveness is the…

Machine Learning · Computer Science 2024-04-15 Nastaran Saadati , Minh Pham , Nasla Saleem , Joshua R. Waite , Aditya Balu , Zhanhong Jiang , Chinmay Hegde , Soumik Sarkar