English
Related papers

Related papers: Logit-Based Losses Limit the Effectiveness of Feat…

200 papers

Knowledge distillation is a common paradigm for transferring capabilities from larger models to smaller ones. While traditional distillation methods leverage a probabilistic divergence over the output of the teacher and student models,…

Machine Learning · Computer Science 2025-10-01 Prajjwal Bhattarai , Mohammad Amjad , Dmytro Zhylko , Tuka Alhanai

Knowledge distillation is often used to transfer knowledge from a strong teacher model to a relatively weak student model. Traditional methods include response-based methods and feature-based methods. Response-based methods are widely used…

Information Retrieval · Computer Science 2023-12-12 Hao Sun , Xiao Liu , Yeyun Gong , Anlei Dong , Jingwen Lu , Yan Zhang , Linjun Yang , Rangan Majumder , Nan Duan

Knowledge distillation is widely applied in various fundamental vision models to enhance the performance of compact models. Existing knowledge distillation methods focus on designing different distillation targets to acquire knowledge from…

Computer Vision and Pattern Recognition · Computer Science 2024-08-23 Yaoze Zhang , Yuming Zhang , Yu Zhao , Yue Zhang , Feiyu Zhu

Knowledge distillation~(KD) has been proved effective for compressing large-scale pre-trained language models. However, existing methods conduct KD statically, e.g., the student model aligns its output distribution to that of a selected…

Computation and Language · Computer Science 2021-09-24 Lei Li , Yankai Lin , Shuhuai Ren , Peng Li , Jie Zhou , Xu Sun

The improvement in the performance of efficient and lightweight models (i.e., the student model) is achieved through knowledge distillation (KD), which involves transferring knowledge from more complex models (i.e., the teacher model).…

Computer Vision and Pattern Recognition · Computer Science 2025-05-20 Seonghak Kim , Gyeongdo Ham , Yucheol Cho , Daeshik Kim

Vision Transformers (ViTs) have achieved significant advancement in computer vision tasks due to their powerful modeling capacity. However, their performance notably degrades when trained with insufficient data due to lack of inherent…

Image and Video Processing · Electrical Eng. & Systems 2025-03-04 Omar S. EL-Assiouti , Ghada Hamed , Dina Khattab , Hala M. Ebied

Several methods of knowledge distillation have been developed for neural network compression. While they all use the KL divergence loss to align the soft outputs of the student model more closely with that of the teacher, the various…

Computer Vision and Pattern Recognition · Computer Science 2020-12-08 Huan Wang , Suhas Lohit , Michael Jones , Yun Fu

Pre-trained language models (PLMs) have emerged as powerful tools for code understanding. However, deploying these PLMs in large-scale applications faces practical challenges due to their computational intensity and inference latency.…

Software Engineering · Computer Science 2025-08-22 Ruiqi Wang , Zezhou Yang , Cuiyun Gao , Xin Xia , Qing Liao

This study proposes a method for knowledge distillation (KD) of fine-tuned Large Language Models (LLMs) into smaller, more efficient, and accurate neural networks. We specifically target the challenge of deploying these models on…

Computation and Language · Computer Science 2024-06-13 Ehsan Latif , Luyang Fang , Ping Ma , Xiaoming Zhai

Knowledge Distillation (KD) is a critical tool for training Large Language Models (LLMs), yet the majority of research focuses on approaches that rely solely on output logits, neglecting semantic information in the teacher's intermediate…

Computation and Language · Computer Science 2026-05-13 Maxime Guigon , Lucas Dixon , Michaël E. Sander

Knowledge Distillation (KD) aims to transfer knowledge from a large teacher model to a smaller student model. While contrastive learning has shown promise in self-supervised learning by creating discriminative representations, its…

Computer Vision and Pattern Recognition · Computer Science 2025-05-14 Nikolaos Giakoumoglou , Tania Stathaki

Knowledge Distillation (KD), aiming to train a better student model by mimicking the teacher model, plays an important role in model compression. One typical way is to align the output logits. However, we find a common issue named…

Computation and Language · Computer Science 2024-09-10 Runming Yang , Taiqiang Wu , Yujiu Yang

Knowledge distillation (KD) is an essential technique to compress large language models (LLMs) into smaller ones. However, despite the distinct roles of the student model and the teacher model in KD, most existing frameworks still use a…

Computation and Language · Computer Science 2026-03-25 Songming Zhang , Xue Zhang , Tong Zhang , Bojie Hu , Yufeng Chen , Jinan Xu

Knowledge distillation (KD) aims at improving the performance of a compact student model by distilling the knowledge from a high-performing teacher model. In this paper, we present an adaptive KD approach, namely AdaDistill, for deep face…

Computer Vision and Pattern Recognition · Computer Science 2024-07-02 Fadi Boutros , Vitomir Štruc , Naser Damer

Online Knowledge Distillation (KD) is recently highlighted to train large models in Federated Learning (FL) environments. Many existing studies adopt the logit ensemble method to perform KD on the server side. However, they often assume…

Machine Learning · Computer Science 2026-01-09 Jihyun Lim , Junhyuk Jo , Tuo Zhang , Sunwoo Lee

Knowledge distillation (KD) is a widely used technique to transfer knowledge from a large teacher network to a smaller student model. Traditional KD uses a fixed balancing factor alpha as a hyperparameter to combine the hard-label…

Computer Vision and Pattern Recognition · Computer Science 2025-09-09 Zhengda Li

Knowledge Distillation is a technique which aims to utilize dark knowledge to compress and transfer information from a vast, well-trained neural network (teacher model) to a smaller, less capable neural network (student model) with improved…

Computer Vision and Pattern Recognition · Computer Science 2022-01-28 Fahad Rahman Amik , Ahnaf Ismat Tasin , Silvia Ahmed , M. M. Lutfe Elahi , Nabeel Mohammed

Knowledge distillation (KD) is a widely adopted approach for compressing large neural networks by transferring knowledge from a large teacher model to a smaller student model. In the context of large language models, token level KD,…

Computation and Language · Computer Science 2025-09-19 Yihan Cao , Yanbin Kang , Zhengming Xing , Ruijie Jiang

Knowledge distillation (KD) techniques have emerged as a powerful tool for transferring expertise from complex teacher models to lightweight student models, particularly beneficial for deploying high-performance models in…

Machine Learning · Computer Science 2025-10-28 Paul Agbaje , Arkajyoti Mitra , Afia Anjum , Pranali Khose , Ebelechukwu Nwafor , Habeeb Olufowobi

Knowledge distillation (KD) is an effective method for model compression and transferring knowledge between models. However, its effect on model's robustness against spurious correlations that degrade performance on out-of-distribution data…

Machine Learning · Computer Science 2025-10-31 Jiali Cheng , Chirag Agarwal , Hadi Amiri
‹ Prev 1 3 4 5 6 7 10 Next ›