English
Related papers

Related papers: Logit Standardization in Knowledge Distillation

200 papers

Knowledge distillation is a technique for improving the performance of a simple "student" model by replacing its one-hot training labels with a distribution over labels obtained from a complex "teacher" model. While this simple approach has…

Machine Learning · Computer Science 2020-05-22 Aditya Krishna Menon , Ankit Singh Rawat , Sashank J. Reddi , Seungyeon Kim , Sanjiv Kumar

Knowledge distillation from large language models (LLMs) assumes that the teacher's output distribution is a high-quality training signal. On reasoning tasks, this assumption is frequently violated. A model's intermediate representations…

Computation and Language · Computer Science 2026-03-16 Ryan Brown , Chris Russell

Knowledge distillation (KD) has become an important technique for model compression and knowledge transfer. In this work, we first perform a comprehensive analysis of the knowledge transferred by different KD methods. We demonstrate that…

Computer Vision and Pattern Recognition · Computer Science 2021-06-07 Fei Ding , Yin Yang , Hongxin Hu , Venkat Krovi , Feng Luo

Knowledge Distillation (KD) is an effective framework for compressing deep learning models, realized by a student-teacher paradigm requiring small student networks to mimic the soft target generated by well-trained teachers. However, the…

Computer Vision and Pattern Recognition · Computer Science 2020-05-20 Yuang Liu , Wei Zhang , Jun Wang

Knowledge distillation is a technique to enhance the generalization ability of a student model by exploiting outputs from a teacher model. Recently, feature-map based variants explore knowledge transfer between manually assigned…

Computer Vision and Pattern Recognition · Computer Science 2021-08-31 Defang Chen , Jian-Ping Mei , Yuan Zhang , Can Wang , Yan Feng , Chun Chen

We introduce the problem of continual distillation learning (CDL) in order to use knowledge distillation (KD) to improve prompt-based continual learning (CL) models. The CDL problem is valuable to study since the use of a larger vision…

Computer Vision and Pattern Recognition · Computer Science 2025-05-21 Qifan Zhang , Yunhui Guo , Yu Xiang

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 common knowledge transfer algorithm used for model compression across a variety of deep learning based natural language processing (NLP) solutions. In its regular manifestations, KD requires access to the…

Computation and Language · Computer Science 2021-01-01 Ahmad Rashid , Vasileios Lioutas , Abbas Ghaddar , Mehdi Rezagholizadeh

Knowledge distillation is an efficient strategy to use data generated by large "teacher" language models to train smaller capable "student" models, but selecting the optimal teacher for a specific student-task combination requires expensive…

Machine Learning · Computer Science 2025-12-23 Abhishek Panigrahi , Bingbin Liu , Sadhika Malladi , Sham Kakade , Surbhi Goel

Knowledge distillation (KD) transfers capabilities from large language models (LLMs) to smaller students, yet it can fail unpredictably and also underpins model leakage risks. Our analysis revealed several distillation traps: tail noise,…

Machine Learning · Computer Science 2026-04-22 Weixiao Zhan , Yongcheng Jing , Leszek Rutkowski , Dacheng Tao

Algorithmic efficiency techniques such as distillation (\cite{hinton2015distillation}) are useful in improving model quality without increasing serving costs, provided a larger teacher model is available for a smaller student model to learn…

Machine Learning · Computer Science 2025-10-09 Khoa Trinh , Gaurav Menghani , Erik Vee

The outpouring of various pre-trained models empowers knowledge distillation by providing abundant teacher resources, but there lacks a developed mechanism to utilize these teachers adequately. With a massive model repository composed of…

Machine Learning · Computer Science 2022-09-29 Su Lu , Han-Jia Ye , De-Chuan Zhan

High storage and computational costs obstruct deep neural networks to be deployed on resource-constrained devices. Knowledge distillation aims to train a compact student network by transferring knowledge from a larger pre-trained teacher…

Computer Vision and Pattern Recognition · Computer Science 2025-10-01 Haoran Zhao , Xin Sun , Junyu Dong , Changrui Chen , Zihe Dong

This work introduces a novel knowledge distillation framework for classification tasks where information on existing subclasses is available and taken into consideration. In classification tasks with a small number of classes or binary…

Machine Learning · Computer Science 2022-07-06 Ahmad Sajedi , Konstantinos N. Plataniotis

Knowledge distillation aims at transferring knowledge acquired in one model (a teacher) to another model (a student) that is typically smaller. Previous approaches can be expressed as a form of training the student to mimic output…

Computer Vision and Pattern Recognition · Computer Science 2019-05-02 Wonpyo Park , Dongju Kim , Yan Lu , Minsu Cho

In recent years, large language models (LLMs) have shown exceptional capabilities across various natural language processing (NLP) tasks. However, such impressive performance often comes with the trade-off of an increased parameter size,…

Computation and Language · Computer Science 2025-02-19 Minchong Li , Feng Zhou , Xiaohui Song

Knowledge distillation (KD) enhances the performance of a student network by allowing it to learn the knowledge transferred from a teacher network incrementally. Existing methods dynamically adjust the temperature to enable the student…

Machine Learning · Computer Science 2026-02-03 Zhengbo Zhang , Yuxi Zhou , Jia Gong , Jun Liu , Zhigang Tu

Knowledge distillation is a potential solution for model compression. The idea is to make a small student network imitate the target of a large teacher network, then the student network can be competitive to the teacher one. Most previous…

Computer Vision and Pattern Recognition · Computer Science 2017-10-24 Chong Wang , Xipeng Lan , Yangang Zhang

Ensemble knowledge distillation can extract knowledge from multiple teacher models and encode it into a single student model. Many existing methods learn and distill the student model on labeled data only. However, the teacher models are…

Machine Learning · Computer Science 2022-04-04 Chuhan Wu , Fangzhao Wu , Tao Qi , Yongfeng Huang

Knowledge distillation (KD) is an efficient approach to transfer the knowledge from a large "teacher" network to a smaller "student" network. Traditional KD methods require lots of labeled training samples and a white-box teacher…

Computer Vision and Pattern Recognition · Computer Science 2022-07-26 Dang Nguyen , Sunil Gupta , Kien Do , Svetha Venkatesh