English
Related papers

Related papers: What Should Feature Distillation Transfer in LLMs?…

200 papers

Knowledge distillation (KD) aims to transfer knowledge from a large teacher model to a smaller student model. Previous work applying KD in the field of large language models (LLMs) typically focused on the post-training phase, where the…

Computation and Language · Computer Science 2024-10-22 Hao Peng , Xin Lv , Yushi Bai , Zijun Yao , Jiajie Zhang , Lei Hou , Juanzi Li

This study proposes a knowledge distillation algorithm based on large language models and feature alignment, aiming to effectively transfer the knowledge of large pre-trained models into lightweight student models, thereby reducing…

Computation and Language · Computer Science 2024-12-30 Shuo Wang , Chihang Wang , Jia Gao , Zhen Qi , Hongye Zheng , Xiaoxuan Liao

Knowledge distillation extracts general knowledge from a pre-trained teacher network and provides guidance to a target student network. Most studies manually tie intermediate features of the teacher and student, and transfer knowledge…

Machine Learning · Computer Science 2021-02-08 Mingi Ji , Byeongho Heo , Sungrae Park

Knowledge distillation (KD) is an effective framework that aims to transfer meaningful information from a large teacher to a smaller student. Generally, KD often involves how to define and transfer knowledge. Previous KD methods often focus…

Computer Vision and Pattern Recognition · Computer Science 2022-07-26 Chuanguang Yang , Zhulin An , Linhang Cai , Yongjun Xu

Does Knowledge Distillation (KD) really work? Conventional wisdom viewed it as a knowledge transfer procedure where a perfect mimicry of the student to its teacher is desired. However, paradoxical studies indicate that closely replicating…

Machine Learning · Computer Science 2024-05-03 Chenqi Guo , Shiwei Zhong , Xiaofeng Liu , Qianli Feng , Yinglong Ma

Knowledge Distillation is crucial for optimizing face recognition models for deployment in computationally limited settings, such as edge devices. Traditional KD methods, such as Raw L2 Feature Distillation or Feature Consistency loss,…

Computer Vision and Pattern Recognition · Computer Science 2025-08-18 Durgesh Mishra , Rishabh Uikey

Knowledge distillation (KD) has been widely used to transfer knowledge from large, accurate models (teachers) to smaller, efficient ones (students). Recent methods have explored enforcing consistency by incorporating causal interpretations…

Computer Vision and Pattern Recognition · Computer Science 2025-07-17 Nikolaos Giakoumoglou , Tania Stathaki

Distributed learning frameworks often rely on exchanging model parameters across workers, instead of revealing their raw data. A prime example is federated learning that exchanges the gradients or weights of each neural network model. Under…

Machine Learning · Computer Science 2020-11-05 Hyowoon Seo , Jihong Park , Seungeun Oh , Mehdi Bennis , Seong-Lyun Kim

In recent years, deep learning has spread rapidly, and deeper, larger models have been proposed. However, the calculation cost becomes enormous as the size of the models becomes larger. Various techniques for compressing the size of the…

Machine Learning · Computer Science 2020-04-20 Hideki Oki , Motoshi Abe , Junichi Miyao , Takio Kurita

Knowledge distillation (KD) is a model compression technique that transfers knowledge from a large teacher model to a smaller student model to enhance its performance. Existing methods often assume that the student model is inherently…

Computer Vision and Pattern Recognition · Computer Science 2024-12-16 Jianhua Zhang , Yi Gao , Ruyu Liu , Xu Cheng , Houxiang Zhang , Shengyong Chen

Knowledge distillation is an attractive approach for learning compact deep neural networks, which learns a lightweight student model by distilling knowledge from a complex teacher model. Attention-based knowledge distillation is a specific…

Computer Vision and Pattern Recognition · Computer Science 2024-03-12 Cuong Pham , Van-Anh Nguyen , Trung Le , Dinh Phung , Gustavo Carneiro , Thanh-Toan Do

Knowledge distillation (KD) is widely used for compressing a teacher model to reduce its inference cost and memory footprint, by training a smaller student model. However, current KD methods for auto-regressive sequence models suffer from…

Machine Learning · Computer Science 2024-01-18 Rishabh Agarwal , Nino Vieillard , Yongchao Zhou , Piotr Stanczyk , Sabela Ramos , Matthieu Geist , Olivier Bachem

Knowledge distillation (KD) is a widely adopted and effective method for compressing models in object detection tasks. Particularly, feature-based distillation methods have shown remarkable performance. Existing approaches often ignore the…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Junfei Yi , Jianxu Mao , Tengfei Liu , Mingjie Li , Hanyu Gu , Hui Zhang , Xiaojun Chang , Yaonan Wang

Knowledge distillation (KD) has shown very promising capabilities in transferring learning representations from large models (teachers) to small models (students). However, as the capacity gap between students and teachers becomes larger,…

Computer Vision and Pattern Recognition · Computer Science 2023-03-24 Zengyu Qiu , Xinzhu Ma , Kunlin Yang , Chunya Liu , Jun Hou , Shuai Yi , Wanli Ouyang

Knowledge distillation has attracted a great deal of interest recently to compress pre-trained language models. However, existing knowledge distillation methods suffer from two limitations. First, the student model simply imitates the…

Computation and Language · Computer Science 2023-05-18 Siyue Wu , Hongzhan Chen , Xiaojun Quan , Qifan Wang , Rui Wang

Knowledge distillation (KD), known for its ability to transfer knowledge from a cumbersome network (teacher) to a lightweight one (student) without altering the architecture, has been garnering increasing attention. Two primary categories…

Computer Vision and Pattern Recognition · Computer Science 2024-09-30 Yaomin Huang , Zaomin Yan , Chaomin Shen , Faming Fang , Guixu Zhang

Multi-teacher Knowledge Distillation (KD) transfers diverse knowledge from a teacher pool to a student network. The core problem of multi-teacher KD is how to balance distillation strengths among various teachers. Most existing methods…

Computer Vision and Pattern Recognition · Computer Science 2025-02-27 Chuanguang Yang , Xinqiang Yu , Han Yang , Zhulin An , Chengqing Yu , Libo Huang , Yongjun Xu

Knowledge distillation transfers knowledge from large teacher models to smaller students for efficient inference. While existing methods primarily focus on distillation strategies, they often overlook the importance of enhancing teacher…

Computer Vision and Pattern Recognition · Computer Science 2026-03-26 Xin Zhang , Jianyang Xu , Hao Peng , Dongjing Wang , Jingyuan Zheng , Yu Li , Yuyu Yin , Hongbo Wang

For visual recognition, knowledge distillation typically involves transferring knowledge from a large, well-trained teacher model to a smaller student model. In this paper, we introduce an effective method to distill knowledge from an…

Computer Vision and Pattern Recognition · Computer Science 2024-09-02 Zaiwei Zhang , Gregory P. Meyer , Zhichao Lu , Ashish Shrivastava , Avinash Ravichandran , Eric M. Wolff

Knowledge distillation (KD) involves transferring knowledge from a pre-trained heavy teacher model to a lighter student model, thereby reducing the inference cost while maintaining comparable effectiveness. Prior KD techniques typically…

Computer Vision and Pattern Recognition · Computer Science 2025-10-17 Jhe-Hao Lin , Yi Yao , Chan-Feng Hsu , Hongxia Xie , Hong-Han Shuai , Wen-Huang Cheng
‹ Prev 1 3 4 5 6 7 10 Next ›