English
Related papers

Related papers: Distillation Scaling Laws

200 papers

Self-supervised learning solves pretext prediction tasks that do not require annotations to learn feature representations. For vision tasks, pretext tasks such as predicting rotation, solving jigsaw are solely created from the input data.…

Computer Vision and Pattern Recognition · Computer Science 2021-07-01 Prashant Bhat , Elahe Arani , Bahram Zonooz

Knowledge distillation is to transfer the knowledge from the data learned by the teacher network to the student network, so that the student has the advantage of less parameters and less calculations, and the accuracy is close to the…

Machine Learning · Computer Science 2020-06-03 Zaida Zhou , Chaoran Zhuge , Xinwei Guan , Wen Liu

Dataset distillation compresses a large dataset into a small synthetic dataset such that learning on the synthetic dataset approximates learning on the original. Training on the distilled dataset can be performed in as little as one step of…

Machine Learning · Computer Science 2025-08-14 Connor Wilhelm , Dan Ventura

This paper proposes the DistillCSE framework, which performs contrastive learning under the self-training paradigm with knowledge distillation. The potential advantage of DistillCSE is its self-enhancing feature: using a base model to…

Computation and Language · Computer Science 2023-12-25 Jiahao Xu , Wei Shao , Lihui Chen , Lemao Liu

There is a growing discrepancy in computer vision between large-scale models that achieve state-of-the-art performance and models that are affordable in practical applications. In this paper we address this issue and significantly bridge…

Computer Vision and Pattern Recognition · Computer Science 2022-06-22 Lucas Beyer , Xiaohua Zhai , Amélie Royer , Larisa Markeeva , Rohan Anil , Alexander Kolesnikov

The proliferation of diffusion models trained on web-scale, provenance-uncertain image collections has made it essential, yet technically unresolved, to determine whether a model has learned from specific copyrighted data without…

Machine Learning · Computer Science 2026-04-06 Muxing Li , Zesheng Ye , Sharon Li , Andy Song , Guangquan Zhang , Feng Liu

Black-box risk scoring models permeate our lives, yet are typically proprietary or opaque. We propose Distill-and-Compare, a model distillation and comparison approach to audit such models. To gain insight into black-box models, we treat…

Machine Learning · Statistics 2018-10-12 Sarah Tan , Rich Caruana , Giles Hooker , Yin Lou

Compressing deep networks is essential to expand their range of applications to constrained settings. The need for compression however often arises long after the model was trained, when the original data might no longer be available. On…

Machine Learning · Computer Science 2022-01-19 Jean-Michel Begon , Pierre Geurts

Model distillation typically focuses on behavioral mimicry, where a student model is trained to replicate a teacher's output while treating its internal computations as a black box. In this work we propose an alternative approach:…

Computation and Language · Computer Science 2025-09-30 Somin Wadhwa , Silvio Amir , Byron C. Wallace

Data distillation is the problem of reducing the volume oftraining data while keeping only the necessary information. With thispaper, we deeper explore the new data distillation algorithm, previouslydesigned for image data. Our experiments…

Machine Learning · Computer Science 2020-10-21 Dmitry Medvedev , Alexander D'yakonov

Training large AI models typically requires large-scale datasets in the machine learning process, making training and parameter-tuning process both time-consuming and costly. Some researchers address this problem by carefully synthesizing a…

Computer Vision and Pattern Recognition · Computer Science 2023-11-28 Jiyuan Shen , Wenzhuo Yang , Kwok-Yan Lam

On-policy distillation (OPD) has become a core technique in the post-training of large language models, yet its training dynamics remain poorly understood. This paper provides a systematic investigation of OPD dynamics and mechanisms. We…

Machine Learning · Computer Science 2026-04-16 Yaxuan Li , Yuxin Zuo , Bingxiang He , Jinqian Zhang , Chaojun Xiao , Cheng Qian , Tianyu Yu , Huan-ang Gao , Wenkai Yang , Zhiyuan Liu , Ning Ding

With the success of deep neural networks, knowledge distillation which guides the learning of a small student network from a large teacher network is being actively studied for model compression and transfer learning. However, few studies…

Computer Vision and Pattern Recognition · Computer Science 2021-08-10 Wonchul Son , Jaemin Na , Junyong Choi , Wonjun Hwang

Knowledge distillation is an effective technique that transfers knowledge from a large teacher model to a shallow student. However, just like massive classification, large scale knowledge distillation also imposes heavy computational costs…

Machine Learning · Computer Science 2018-12-04 Minghan Li , Tanli Zuo , Ruicheng Li , Martha White , Weishi Zheng

This paper proposes a novel knowledge distillation-based learning method to improve the classification performance of convolutional neural networks (CNNs) without a pre-trained teacher network, called exit-ensemble distillation. Our method…

Computer Vision and Pattern Recognition · Computer Science 2021-04-06 Hojung Lee , Jong-Seok Lee

We study policy distillation under privileged information, where a student policy with only partial observations must learn from a teacher with full-state access. A key challenge is information asymmetry: the student cannot directly access…

Robotics · Computer Science 2025-05-15 Yujin Kim , Nathaniel Chin , Arnav Vasudev , Sanjiban Choudhury

We propose a novel knowledge distillation approach to facilitate the transfer of dark knowledge from a teacher to a student. Contrary to most of the existing methods that rely on effective training of student models given pretrained…

Machine Learning · Computer Science 2022-01-25 Dae Young Park , Moon-Hyun Cha , Changwook Jeong , Dae Sin Kim , Bohyung Han

Recently, research efforts have been concentrated on revealing how pre-trained model makes a difference in neural network performance. Self-supervision and semi-supervised learning technologies have been extensively explored by the…

Computer Vision and Pattern Recognition · Computer Science 2021-03-11 Cheng Cui , Ruoyu Guo , Yuning Du , Dongliang He , Fu Li , Zewu Wu , Qiwen Liu , Shilei Wen , Jizhou Huang , Xiaoguang Hu , Dianhai Yu , Errui Ding , Yanjun Ma

Knowledge Distillation (KD) is a widespread technique for compressing the knowledge of large models into more compact and efficient models. KD has proved to be highly effective in building well-performing low-complexity Acoustic Scene…

Sound · Computer Science 2025-03-17 Tobias Morocutti , Florian Schmid , Khaled Koutini , Gerhard Widmer

Distillation-based learning boosts the performance of the miniaturized neural network based on the hypothesis that the representation of a teacher model can be used as structured and relatively weak supervision, and thus would be easily…

Machine Learning · Computer Science 2019-04-22 Xiao Jin , Baoyun Peng , Yichao Wu , Yu Liu , Jiaheng Liu , Ding Liang , Junjie Yan , Xiaolin Hu
‹ Prev 1 8 9 10 Next ›