English
Related papers

Related papers: Circuit Distillation

200 papers

We propose a distillation scaling law that estimates distilled model performance based on a compute budget and its allocation between the student and teacher. Our findings mitigate the risks associated with large-scale distillation by…

Machine Learning · Computer Science 2025-07-28 Dan Busbridge , Amitis Shidani , Floris Weers , Jason Ramapuram , Etai Littwin , Russ Webb

Knowledge distillation is a technique to enhance the generalization ability of a student model by exploiting outputs from a teacher model. Recently, feature-map based variants explore knowledge transfer between manually assigned…

Computer Vision and Pattern Recognition · Computer Science 2021-08-31 Defang Chen , Jian-Ping Mei , Yuan Zhang , Can Wang , Yan Feng , Chun Chen

The crux of knowledge distillation is to effectively train a resource-limited student model with the guide of a pre-trained larger teacher model. However, when there is a large difference between the model complexities of teacher and…

Machine Learning · Computer Science 2021-06-01 Aryan Asadian , Amirali Salehi-Abari

The vulnerability of artificial neural networks to adversarial perturbations in the black-box setting is widely studied in the literature. The majority of attack methods to construct these perturbations suffer from an impractically large…

Machine Learning · Computer Science 2024-10-22 Kirill Lukyanov , Andrew Perminov , Denis Turdakov , Mikhail Pautov

Top-performing machine learning systems, such as deep neural networks, large ensembles and complex probabilistic graphical models, can be expensive to store, slow to evaluate and hard to integrate into larger systems. Ideally, we would like…

Machine Learning · Statistics 2015-10-09 George Papamakarios

Deep learning achieved great progress recently, however, it is not easy or efficient to further improve its performance by increasing the size of the model. Multi-modal learning can mitigate this challenge by introducing richer and more…

Artificial Intelligence · Computer Science 2025-10-07 Cairong Zhao , Yufeng Jin , Zifan Song , Haonan Chen , Duoqian Miao , Guosheng Hu

Knowledge distillation allows smaller neural networks to emulate the performance of larger, teacher models with reduced computational demands. Traditional methods for Large Language Models (LLMs) often necessitate extensive fine-tuning,…

Computation and Language · Computer Science 2025-05-02 Tyler McDonald , Ali Emami

It has been commonly observed that a teacher model with superior performance does not necessarily result in a stronger student, highlighting a discrepancy between current teacher training practices and effective knowledge transfer. In order…

Computation and Language · Computer Science 2024-05-16 Yuxin Ren , Zihan Zhong , Xingjian Shi , Yi Zhu , Chun Yuan , Mu Li

Large language models (LLMs) excel in complex reasoning tasks, and distilling their reasoning capabilities into smaller models has shown promise. However, we uncover an interesting phenomenon, which we term the Small Model Learnability Gap:…

Artificial Intelligence · Computer Science 2025-11-14 Yuetai Li , Xiang Yue , Zhangchen Xu , Fengqing Jiang , Luyao Niu , Bill Yuchen Lin , Bhaskar Ramasubramanian , Radha Poovendran

Knowledge distillation (KD) is an effective technique to transfer knowledge from one neural network (teacher) to another (student), thus improving the performance of the student. To make the student better mimic the behavior of the teacher,…

Machine Learning · Computer Science 2020-10-20 Xiang Deng , Zhongfei , Zhang

Knowledge distillation provides an effective way to transfer knowledge via teacher-student learning, where most existing distillation approaches apply a fixed pre-trained model as teacher to supervise the learning of student network. This…

Machine Learning · Computer Science 2021-03-26 Kangkai Zhang , Chunhui Zhang , Shikun Li , Dan Zeng , Shiming Ge

While diffusion models effectively generate remarkable synthetic images, a key limitation is the inference inefficiency, requiring numerous sampling steps. To accelerate inference and maintain high-quality synthesis, teacher-student…

Computer Vision and Pattern Recognition · Computer Science 2024-05-27 Chi Hong , Jiyue Huang , Robert Birke , Dick Epema , Stefanie Roos , Lydia Y. Chen

Knowledge distillation, i.e., one classifier being trained on the outputs of another classifier, is an empirically very successful technique for knowledge transfer between classifiers. It has even been observed that classifiers learn much…

Machine Learning · Computer Science 2021-05-28 Mary Phuong , Christoph H. Lampert

As a technique to bridge logit matching and probability distribution matching, temperature scaling plays a pivotal role in knowledge distillation (KD). Conventionally, temperature scaling is applied to both teacher's logits and student's…

Machine Learning · Computer Science 2024-03-11 Kaixiang Zheng , En-Hui Yang

Knowledge distillation is a key technique for transferring the capabilities of large language models (LLMs) into smaller, more efficient student models. Existing distillation approaches often overlook two critical factors: the learning…

Machine Learning · Computer Science 2026-05-13 Jincheng Cao , Fanzhi Zeng , Leqi Liu , Aryan Mokhtari

Knowledge distillation (KD) transfers capabilities from large language models (LLMs) to smaller students, yet it can fail unpredictably and also underpins model leakage risks. Our analysis revealed several distillation traps: tail noise,…

Machine Learning · Computer Science 2026-04-22 Weixiao Zhan , Yongcheng Jing , Leszek Rutkowski , Dacheng Tao

Large language models (LLMs) are known to memorize parts of their training data, raising important concerns around privacy and security. While previous research has focused on studying memorization in pre-trained models, much less is known…

Machine Learning · Computer Science 2025-08-19 Simardeep Singh

Knowledge distillation (KD) is commonly deemed as an effective model compression technique in which a compact model (student) is trained under the supervision of a larger pretrained model or an ensemble of models (teacher). Various…

Machine Learning · Computer Science 2020-07-08 Fahad Sarfraz , Elahe Arani , Bahram Zonooz

Contrastive Language-Image Pre-training (CLIP) has been shown to improve zero-shot generalization capabilities of language and vision models. In this paper, we extend CLIP for efficient knowledge distillation, by utilizing embeddings as…

Machine Learning · Computer Science 2024-09-02 Lakshmi Nair

Purpose: In curriculum learning, the idea is to train on easier samples first and gradually increase the difficulty, while in self-paced learning, a pacing function defines the speed to adapt the training progress. While both methods…

Computer Vision and Pattern Recognition · Computer Science 2023-02-03 Mobarakol Islam , Lalithkumar Seenivasan , S. P. Sharan , V. K. Viekash , Bhavesh Gupta , Ben Glocker , Hongliang Ren