English
Related papers

Related papers: Distillation Scaling Laws

200 papers

Knowledge distillation is typically conducted by training a small model (the student) to mimic a large and cumbersome model (the teacher). The idea is to compress the knowledge from the teacher by using its output probabilities as…

Computation and Language · Computer Science 2020-01-17 Gustavo Aguilar , Yuan Ling , Yu Zhang , Benjamin Yao , Xing Fan , Chenlei Guo

Large-scale language models have recently demonstrated impressive empirical performance. Nevertheless, the improved results are attained at the price of bigger models, more power consumption, and slower inference, which hinder their…

Computation and Language · Computer Science 2021-03-18 Kevin J Liang , Weituo Hao , Dinghan Shen , Yufan Zhou , Weizhu Chen , Changyou Chen , Lawrence Carin

On-policy distillation is an efficient alternative to reinforcement learning, offering dense token-level training signals. However, its reliance on a stronger external teacher has driven recent work on on-policy self-distillation, where the…

Machine Learning · Computer Science 2026-05-07 Xin Yu , Liuchen Liao , Yiwen Zhang , Yingchen Yu , Lingzhou Xue , Qinzhen Guo

Advances in self-distillation have shown that when knowledge is distilled from a teacher to a student using the same deep learning (DL) architecture, the student performance can surpass the teacher particularly when the network is…

Machine Learning · Computer Science 2025-06-25 Muhammad Haseeb Aslam , Clara Martinez , Marco Pedersoli , Alessandro Koerich , Ali Etemad , Eric Granger

Large neural models (such as Transformers) achieve state-of-the-art performance for information retrieval (IR). In this paper, we aim to improve distillation methods that pave the way for the resource-efficient deployment of such models in…

Model distillation has been a popular method for producing interpretable machine learning. It uses an interpretable "student" model to mimic the predictions made by the black box "teacher" model. However, when the student model is sensitive…

Machine Learning · Statistics 2023-05-01 Yunzhe Zhou , Peiru Xu , Giles Hooker

The computational benefits of iterative non-autoregressive transformers decrease as the number of decoding steps increases. As a remedy, we introduce Distill Multiple Steps (DiMS), a simple yet effective distillation technique to decrease…

Computation and Language · Computer Science 2023-06-13 Sajad Norouzi , Rasa Hosseinzadeh , Felipe Perez , Maksims Volkovs

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

We introduce Proximal Policy Distillation (PPD), a novel policy distillation method that integrates student-driven distillation and Proximal Policy Optimization (PPO) to increase sample efficiency and to leverage the additional rewards that…

Machine Learning · Computer Science 2026-05-11 Giacomo Spigler

Knowledge distillation is considered as a training and compression strategy in which two neural networks, namely a teacher and a student, are coupled together during training. The teacher network is supposed to be a trustworthy predictor…

Computation and Language · Computer Science 2020-12-29 Peyman Passban , Yimeng Wu , Mehdi Rezagholizadeh , Qun Liu

On-policy distillation (OPD), which aligns the student with the teacher's logit distribution on student-generated trajectories, has demonstrated strong empirical gains in improving student performance and often outperforms off-policy…

Machine Learning · Computer Science 2026-02-27 Wenkai Yang , Weijie Liu , Ruobing Xie , Kai Yang , Saiyong Yang , Yankai Lin

In this work, we investigate the implicit regularization induced by teacher-student learning dynamics in self-distillation. To isolate its effect, we describe a simple experiment where we consider teachers at random initialization instead…

Machine Learning · Computer Science 2023-07-06 Felix Sarnthein , Gregor Bachmann , Sotiris Anagnostidis , Thomas Hofmann

Dataset distillation is the task of synthesizing a small dataset such that a model trained on the synthetic set will match the test accuracy of the model trained on the full dataset. In this paper, we propose a new formulation that…

Computer Vision and Pattern Recognition · Computer Science 2022-03-23 George Cazenavette , Tongzhou Wang , Antonio Torralba , Alexei A. Efros , Jun-Yan Zhu

Knowledge distillation is a widely applicable technique for training a student neural network under the guidance of a trained teacher network. For example, in neural network compression, a high-capacity teacher is distilled to train a…

Computer Vision and Pattern Recognition · Computer Science 2019-08-05 Frederick Tung , Greg Mori

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

Knowledge distillation is a critical technique to transfer knowledge between models, typically from a large model (the teacher) to a more fine-grained one (the student). The objective function of knowledge distillation is typically the…

Computation and Language · Computer Science 2021-06-03 Xinyu Wang , Yong Jiang , Zhaohui Yan , Zixia Jia , Nguyen Bach , Tao Wang , Zhongqiang Huang , Fei Huang , Kewei Tu

Knowledge distillation (KD) has been widely used to improve the test accuracy of a "student" network, by training it to mimic the soft probabilities of a trained "teacher" network. Yet, it has been shown in recent work that, despite being…

Machine Learning · Computer Science 2024-03-20 Vaishnavh Nagarajan , Aditya Krishna Menon , Srinadh Bhojanapalli , Hossein Mobahi , Sanjiv Kumar

Knowledge distillation transfers the knowledge from a cumbersome teacher to a small student. Recent results suggest that the student-friendly teacher is more appropriate to distill since it provides more transferable knowledge. In this…

Machine Learning · Computer Science 2022-07-26 Jinhyuk Park , Albert No

Knowledge distillation (KD) has emerged as a promising technique for addressing the computational challenges associated with deploying large-scale recommender systems. KD transfers the knowledge of a massive teacher system to a compact…

Information Retrieval · Computer Science 2024-06-27 Gyuseok Lee , SeongKu Kang , Wonbin Kweon , Hwanjo Yu

This position paper argues that knowledge distillation must account for what it loses: student models should be judged not only by retained task scores, but by whether they preserve the teacher capabilities that make those scores reliable.…

Machine Learning · Computer Science 2026-05-07 Wenshuo Wang
‹ Prev 1 4 5 6 7 8 10 Next ›