English
Related papers

Related papers: Over-parameterized Student Model via Tensor Decomp…

200 papers

Knowledge Distillation (KD) is one of the approaches to reduce the size of Large Language Models (LLMs). A LLM with smaller number of model parameters (student) is trained to mimic the performance of a LLM of a larger size (teacher model)…

Computation and Language · Computer Science 2025-04-29 Rishika Sen , Sujoy Roychowdhury , Sumit Soman , H. G. Ranjani , Srikhetra Mohanty

Knowledge distillation (KD) is a core component in the training and deployment of modern generative models, particularly large language models (LLMs). While its empirical benefits are well documented -- enabling smaller student models to…

Machine Learning · Computer Science 2026-01-16 Sungmin Cha , Kyunghyun Cho

Pre-trained language models such as BERT have proven to be highly effective for natural language processing (NLP) tasks. However, the high demand for computing resources in training such models hinders their application in practice. In…

Computation and Language · Computer Science 2019-08-27 Siqi Sun , Yu Cheng , Zhe Gan , Jingjing Liu

Modern search systems use several large ranker models with transformer architectures. These models require large computational resources and are not suitable for usage on devices with limited computational resources. Knowledge distillation…

Self-supervised pre-training is an effective approach to leveraging a large amount of unlabelled data to reduce word error rates (WERs) of automatic speech recognition (ASR) systems. Since it is impractical to use large pre-trained models…

Audio and Speech Processing · Electrical Eng. & Systems 2022-03-03 Xiaoyu Yang , Qiujia Li , Philip C. Woodland

Knowledge distillation (KD) is a promising yet challenging model compression technique that transfers rich learning representations from a well-performing but cumbersome teacher model to a compact student model. Previous methods for image…

Computer Vision and Pattern Recognition · Computer Science 2024-04-04 Simiao Li , Yun Zhang , Wei Li , Hanting Chen , Wenjia Wang , Bingyi Jing , Shaohui Lin , Jie Hu

Knowledge distillation (KD) is widely used to train small, high-performing student language models (LMs) using large teacher LMs. While effective in fine-tuning, KD during pre-training faces efficiency, flexibility, and effectiveness…

Computation and Language · Computer Science 2025-03-20 Yuxian Gu , Hao Zhou , Fandong Meng , Jie Zhou , Minlie Huang

Knowledge Distillation (KD) compresses large language models (LLMs) by transferring the teacher model's capabilities to a smaller student model, reducing inference cost and memory usage while maintaining performance. However, existing KD…

Computation and Language · Computer Science 2025-06-11 Lingyuan Liu , Mengxiang Zhang

Knowledge Distillation (KD) can transfer the reasoning abilities of large models to smaller ones, which can reduce the costs to generate Chain-of-Thoughts for reasoning tasks. KD methods typically ask the student to mimic the teacher's…

Computation and Language · Computer Science 2026-03-17 Minsang Kim , Seung Jun Baek

Existing techniques often attempt to make knowledge transfer from a powerful machine translation (MT) to speech translation (ST) model with some elaborate techniques, which often requires transcription as extra input during training.…

Computation and Language · Computer Science 2023-04-21 Hao Zhang , Nianwen Si , Yaqi Chen , Wenlin Zhang , Xukui Yang , Dan Qu , Zhen Li

Knowledge distillation is an effective way for model compression in deep learning. Given a large model (i.e., teacher model), it aims to improve the performance of a compact model (i.e., student model) by transferring the information from…

Machine Learning · Computer Science 2022-03-31 Qi Qian , Hao Li , Juhua Hu

In knowledge distillation, the knowledge from the teacher model is often too complex for the student model to thoroughly process. However, good teachers in real life always simplify complex material before teaching it to students. Inspired…

Computer Vision and Pattern Recognition · Computer Science 2023-05-19 Mengyang Yuan , Bo Lang , Fengnan Quan

Knowledge distillation (KD) enables a smaller "student" model to mimic a larger "teacher" model by transferring knowledge from the teacher's output or features. However, most KD methods treat all samples uniformly, overlooking the varying…

Computer Vision and Pattern Recognition · Computer Science 2025-08-12 Chi-Ping Su , Ching-Hsun Tseng , Bin Pu , Lei Zhao , Jiewen Yang , Zhuangzhuang Chen , Shin-Jye Lee

Efficient deployment of deep neural networks on resource-constrained devices demands advanced compression techniques that preserve accuracy and interoperability. This paper proposes a machine learning framework that augments Knowledge…

Machine Learning · Computer Science 2025-03-18 David E. Hernandez , Jose Ramon Chang , Torbjörn E. M. Nordling

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

Recent advancements in large language models (LLMs) have raised concerns about inference costs, increasing the need for research into model compression. While knowledge distillation (KD) is a prominent method for this, research on KD for…

Computation and Language · Computer Science 2024-09-30 Gyeongman Kim , Doohyuk Jang , Eunho Yang

Knowledge Distillation (KD) compresses computationally expensive pre-trained language models (PLMs) by transferring their knowledge to smaller models, allowing their use in resource-constrained or real-time settings. However, most smaller…

Computation and Language · Computer Science 2023-11-08 Hayeon Lee , Rui Hou , Jongpil Kim , Davis Liang , Hongbo Zhang , Sung Ju Hwang , Alexander Min

Knowledge distillation (KD) is a well-known method for compressing neural models. However, works focusing on distilling knowledge from large multilingual neural machine translation (MNMT) models into smaller ones are practically…

Computation and Language · Computer Science 2023-04-20 Varun Gumma , Raj Dabre , Pratyush Kumar

Recently, large-scale pre-trained models have shown their advantages in many tasks. However, due to the huge computational complexity and storage requirements, it is challenging to apply the large-scale model to real scenes. A common…

Computer Vision and Pattern Recognition · Computer Science 2022-12-27 Deng Li , Aming Wu , Yahong Han , Qi Tian

Layer-wise distillation is a powerful tool to compress large models (i.e. teacher models) into small ones (i.e., student models). The student distills knowledge from the teacher by mimicking the hidden representations of the teacher at…

Computation and Language · Computer Science 2023-06-07 Chen Liang , Simiao Zuo , Qingru Zhang , Pengcheng He , Weizhu Chen , Tuo Zhao