English
Related papers

Related papers: On-Policy Distillation of Language Models: Learnin…

200 papers

A recent trend in Natural Language Processing is the exponential growth in Language Model (LM) size, which prevents research groups without a necessary hardware infrastructure from participating in the development process. This study…

Computation and Language · Computer Science 2023-01-31 Jan Philip Wahle

Knowledge distillation (KD), as an efficient and effective model compression technique, has been receiving considerable attention in deep learning. The key to its success is to transfer knowledge from a large teacher network to a small…

Machine Learning · Computer Science 2021-01-28 Liyuan Sun , Jianping Gou , Baosheng Yu , Lan Du , Dacheng Tao

Recent recommender systems have shown remarkable performance by using an ensemble of heterogeneous models. However, it is exceedingly costly because it requires resources and inference latency proportional to the number of models, which…

Information Retrieval · Computer Science 2023-03-03 SeongKu Kang , Wonbin Kweon , Dongha Lee , Jianxun Lian , Xing Xie , Hwanjo Yu

Large language models (LLMs) have demonstrated remarkable performance across a wide range of natural language processing (NLP) tasks. However, these models are often difficult to deploy due to significant computational requirements and…

Computation and Language · Computer Science 2024-12-25 Vijay Goyal , Mustafa Khan , Aprameya Tirupati , Harveer Saini , Michael Lam , Kevin Zhu

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

In the past few years, transformer-based pre-trained language models have achieved astounding success in both industry and academia. However, the large model size and high run-time latency are serious impediments to applying them in…

Computation and Language · Computer Science 2022-07-13 Chengqiang Lu , Jianwei Zhang , Yunfei Chu , Zhengyu Chen , Jingren Zhou , Fei Wu , Haiqing Chen , Hongxia Yang

Knowledge distillation (KD) is known as a promising solution to compress large language models (LLMs) via transferring their knowledge to smaller models. During this process, white-box KD methods usually minimize the distance between the…

Computation and Language · Computer Science 2024-10-02 Songming Zhang , Xue Zhang , Zengkui Sun , Yufeng Chen , Jinan Xu

Tiny, causal models are crucial for embedded audio machine learning applications. Model compression can be achieved via distilling knowledge from a large teacher into a smaller student model. In this work, we propose a novel two-step…

Sound · Computer Science 2023-09-18 Rayan Daod Nathoo , Mikolaj Kegler , Marko Stamenovic

Many existing studies on knowledge distillation have focused on methods in which a student model mimics a teacher model well. Simply imitating the teacher's knowledge, however, is not sufficient for the student to surpass that of the…

Computer Vision and Pattern Recognition · Computer Science 2023-04-19 Jihyeon Seo , Kyusam Oh , Chanho Min , Yongkeun Yun , Sungwoo Cho

Knowledge Distillation (KD) compresses neural networks by learning a small network (student) via transferring knowledge from a pre-trained large network (teacher). Many endeavours have been devoted to the image domain, while few works focus…

Computer Vision and Pattern Recognition · Computer Science 2025-07-08 Ping Li , Chenhao Ping , Wenxiao Wang , Mingli Song

Knowledge distillation (KD) has been a popular and effective method for model compression. One important assumption of KD is that the teacher's original dataset will also be available when training the student. However, in situations such…

Computer Vision and Pattern Recognition · Computer Science 2025-10-03 Logan Frank , Jim Davis

Knowledge distillation compresses a larger neural model (teacher) into smaller, faster student models by training them to match teacher outputs. However, the internal computational transformations that occur during this process remain…

Machine Learning · Computer Science 2026-03-10 Reilly Haskins , Benjamin Adams

Knowledge distillation is an effective technique for pre-trained language model compression. However, existing methods only focus on the knowledge distribution among layers, which may cause the loss of fine-grained information in the…

Computation and Language · Computer Science 2026-04-06 Zihe Liu , Yulong Mao , Jinan Xu , Xinrui Peng , Kaiyu Huang

Knowledge distillation (KD) is a popular method to train efficient networks ("student") with the help of high-capacity networks ("teacher"). Traditional methods use the teacher's soft logits as extra supervision to train the student…

Computer Vision and Pattern Recognition · Computer Science 2021-08-17 Guo-Hua Wang , Yifan Ge , Jianxin Wu

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

Recent research on knowledge distillation has increasingly focused on logit distillation because of its simplicity, effectiveness, and versatility in model compression. In this paper, we introduce Refined Logit Distillation (RLD) to address…

Computer Vision and Pattern Recognition · Computer Science 2025-07-29 Wujie Sun , Defang Chen , Siwei Lyu , Genlang Chen , Chun Chen , Can Wang

Sequence-level knowledge distillation (SLKD) is a model compression technique that leverages large, accurate teacher models to train smaller, under-parameterized student models. Why does pre-processing MT data with SLKD help us train…

Computation and Language · Computer Science 2019-12-10 Mitchell A. Gordon , Kevin Duh

We investigate whether knowledge distillation (KD) from multiple heterogeneous teacher models can enhance the generation of transferable adversarial examples. A lightweight student model is trained using two KD strategies: curriculum-based…

Machine Learning · Computer Science 2025-07-30 Siddhartha Pradhan , Shikshya Shiwakoti , Neha Bathuri

Despite the success of Large Language Models (LLMs), they still face challenges related to high inference costs and memory requirements. To address these issues, Knowledge Distillation (KD) has emerged as a popular method for model…

Computation and Language · Computer Science 2025-04-23 Jahyun Koo , Yerin Hwang , Yongil Kim , Taegwan Kang , Hyunkyung Bae , Kyomin Jung

Recent advancements in Neural Machine Translation (NMT) have significantly improved translation quality. However, the increasing size and complexity of state-of-the-art models present significant challenges for deployment on…

Computation and Language · Computer Science 2026-05-12 Xuewen Zhang , Haixiao Zhang , Xinlong Huang