English
Related papers

Related papers: On Good Practices for Task-Specific Distillation o…

200 papers

Speculative decoding (SD) accelerates large language model inference by employing a faster draft model for generating multiple tokens, which are then verified in parallel by the larger target model, resulting in the text generated according…

Knowledge distillation optimises a smaller student model to behave similarly to a larger teacher model, retaining some of the performance benefits. While this method can improve results on in-distribution examples, it does not necessarily…

Computation and Language · Computer Science 2024-07-26 Joe Stacey , Marek Rei

Training machine learning models on massive datasets is expensive and time-consuming. Dataset distillation addresses this by creating a small synthetic dataset that achieves the same performance as the full dataset. Recent methods use…

Computer Vision and Pattern Recognition · Computer Science 2026-04-02 Jeffrey A. Chan-Santiago , Mubarak Shah

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

Dataset distillation enables the training of deep neural networks with comparable performance in significantly reduced time by compressing large datasets into small and representative ones. Although the introduction of generative models has…

Machine Learning · Computer Science 2025-05-27 Mingzhuo Li , Guang Li , Jiafeng Mao , Takahiro Ogawa , Miki Haseyama

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

This paper studies the potential of distilling knowledge from pre-trained models, especially Masked Autoencoders. Our approach is simple: in addition to optimizing the pixel reconstruction loss on masked inputs, we minimize the distance…

Computer Vision and Pattern Recognition · Computer Science 2022-11-11 Yutong Bai , Zeyu Wang , Junfei Xiao , Chen Wei , Huiyu Wang , Alan Yuille , Yuyin Zhou , Cihang Xie

This paper addresses the challenges of high computational cost and slow inference in deploying large language models. It proposes a distillation strategy guided by multiple teacher models. The method constructs several teacher models and…

Computation and Language · Computer Science 2025-07-22 Xiandong Meng , Yan Wu , Yexin Tian , Xin Hu , Tianze Kang , Junliang Du

Recent advances in knowledge distillation (KD) have enabled smaller student models to approach the performance of larger teacher models. However, popular methods such as supervised KD and on-policy KD, are adversely impacted by the…

Computation and Language · Computer Science 2025-04-29 Wenda Xu , Rujun Han , Zifeng Wang , Long T. Le , Dhruv Madeka , Lei Li , William Yang Wang , Rishabh Agarwal , Chen-Yu Lee , Tomas Pfister

Generalization Performance of Deep Learning models trained using Empirical Risk Minimization can be improved significantly by using Data Augmentation strategies such as simple transformations, or using Mixed Samples. We attempt to…

Computer Vision and Pattern Recognition · Computer Science 2020-06-11 Deepan Das , Haley Massa , Abhimanyu Kulkarni , Theodoros Rekatsinas

Topic models are often used to identify human-interpretable topics to help make sense of large document collections. We use knowledge distillation to combine the best attributes of probabilistic topic models and pretrained transformers. Our…

Computation and Language · Computer Science 2020-10-07 Alexander Hoyle , Pranav Goel , Philip Resnik

Model distillation is an effective and widely used technique to transfer knowledge from a teacher to a student network. The typical application is to transfer from a powerful large network or ensemble to a small network, that is better…

Computer Vision and Pattern Recognition · Computer Science 2017-06-02 Ying Zhang , Tao Xiang , Timothy M. Hospedales , Huchuan Lu

Distillation is the task of replacing a complicated machine learning model with a simpler model that approximates the original [BCNM06,HVD15]. Despite many practical applications, basic questions about the extent to which models can be…

Machine Learning · Computer Science 2024-05-07 Enric Boix-Adsera

The task of information retrieval is an important component of many natural language processing systems, such as open domain question answering. While traditional methods were based on hand-crafted features, continuous representations based…

Computation and Language · Computer Science 2022-08-05 Gautier Izacard , Edouard Grave

Diffusion models have recently achieved astonishing performance in generating high-fidelity photo-realistic images. Given their huge success, it is still unclear whether synthetic images are applicable for knowledge distillation when real…

Computer Vision and Pattern Recognition · Computer Science 2023-05-23 Zheng Li , Yuxuan Li , Penghai Zhao , Renjie Song , Xiang Li , Jian Yang

Knowledge distillation refers to the process of training a compact student network to achieve better accuracy by learning from a high capacity teacher network. Most of the existing knowledge distillation methods direct the student to follow…

Computer Vision and Pattern Recognition · Computer Science 2020-07-21 Himalaya Jain , Spyros Gidaris , Nikos Komodakis , Patrick Pérez , Matthieu Cord

The widespread deployment of Large Language Models (LLMs) is hindered by the high computational demands, making knowledge distillation (KD) crucial for developing compact smaller ones. However, the conventional KD methods endure the…

Computation and Language · Computer Science 2025-02-18 Zengkui Sun , Yijin Liu , Fandong Meng , Yufeng Chen , Jinan Xu , Jie Zhou

Self-supervised speech pre-training enables deep neural network models to capture meaningful and disentangled factors from raw waveform signals. The learned universal speech representations can then be used across numerous downstream tasks.…

Audio and Speech Processing · Electrical Eng. & Systems 2023-02-24 Heitor R. Guimarães , Arthur Pimentel , Anderson R. Avila , Mehdi Rezagholizadeh , Boxing Chen , Tiago H. Falk

Task-agnostic knowledge distillation attempts to address the problem of deploying large pretrained language model in resource-constrained scenarios by compressing a large pretrained model called teacher into a smaller one called student…

Computation and Language · Computer Science 2023-01-10 Weixin Liu , Xuyi Chen , Jiaxiang Liu , Shikun Feng , Yu Sun , Hao Tian , Hua Wu

State-of-the-art CNN based recognition models are often computationally prohibitive to deploy on low-end devices. A promising high level approach tackling this limitation is knowledge distillation, which let small student model mimic…

Computer Vision and Pattern Recognition · Computer Science 2019-10-31 Tao Wang , Li Yuan , Xiaopeng Zhang , Jiashi Feng