English
Related papers

Related papers: AMiD: Knowledge Distillation for LLMs with $\alpha…

200 papers

While knowledge distillation has become a mature field for compressing large language models (LLMs) into smaller ones by aligning their outputs or internal representations, the distillation of LLM-based agents, which involve planning,…

Artificial Intelligence · Computer Science 2025-06-18 Jiahao Qiu , Xinzhe Juan , Yimin Wang , Ling Yang , Xuan Qi , Tongcheng Zhang , Jiacheng Guo , Yifu Lu , Zixin Yao , Hongru Wang , Shilong Liu , Xun Jiang , Liu Leqi , Mengdi Wang

Knowledge Distillation (KD) has been used in image classification for model compression. However, rare studies apply this technology on single-stage object detectors. Focal loss shows that the accumulated errors of easily-classified samples…

Computer Vision and Pattern Recognition · Computer Science 2019-01-15 Shitao Tang , Litong Feng , Wenqi Shao , Zhanghui Kuang , Wei Zhang , Yimin Chen

Knowledge distillation (KD), as an efficient and effective model compression technique, has been receiving considerable attention in deep learning. The key to its success is to transfer knowledge from a large teacher network to a small…

Machine Learning · Computer Science 2021-01-28 Liyuan Sun , Jianping Gou , Baosheng Yu , Lan Du , Dacheng Tao

In knowledge distillation (KD), logit distillation (LD) aims to transfer class-level knowledge from a more powerful teacher network to a small student model via accurate teacher-student alignment at the logits level. Since high-confidence…

Computer Vision and Pattern Recognition · Computer Science 2025-06-02 Jiayan Li , Jun Li , Zhourui Zhang , Jianhua Xu

Large language models having hundreds of millions, and even billions, of parameters have performed extremely well on a variety of natural language processing (NLP) tasks. Their widespread use and adoption, however, is hindered by the lack…

Computation and Language · Computer Science 2022-12-23 Dan DeGenaro , Jugal Kalita

Knowledge distillation involves transferring the predictive capabilities of large, high-performing AI models (teachers) to smaller models (students) that can operate in environments with limited computing power. In this paper, we address…

Machine Learning · Computer Science 2026-01-12 Pattarawat Chormai , Ali Hashemi , Klaus-Robert Müller , Grégoire Montavon

Knowledge distillation (KD) is a popular method of transferring knowledge from a large "teacher" model to a small "student" model. Previous work has explored various layer-selection strategies (e.g., forward matching and in-order random…

Machine Learning · Computer Science 2025-12-11 Zony Yu , Yuqiao Wen , Lili Mou

Large language models (LLMs) achieve state-of-the-art (SOTA) performance across language tasks, but are costly to deploy due to their size and resource demands. Knowledge Distillation (KD) addresses this by training smaller Student models…

Computation and Language · Computer Science 2026-05-19 Stella Eva Tsiapali , Cong-Thanh Do , Kate Knill

Multi-teacher knowledge distillation (KD), a more effective technique than traditional single-teacher methods, transfers knowledge from expert teachers to a compact student model using logit or feature matching. However, most existing…

Computer Vision and Pattern Recognition · Computer Science 2025-11-13 Amir M. Mansourian , Amir Mohammad Babaei , Shohreh Kasaei

Kullback-Leiber divergence has been widely used in Knowledge Distillation (KD) to compress Large Language Models (LLMs). Contrary to prior assertions that reverse Kullback-Leibler (RKL) divergence is mode-seeking and thus preferable over…

Computation and Language · Computer Science 2024-12-10 Taiqiang Wu , Chaofan Tao , Jiahao Wang , Runming Yang , Zhe Zhao , Ngai Wong

In-context learning (ICL) allows large language models (LLMs) to solve novel tasks without weight updates. Despite its empirical success, the mechanism behind ICL remains poorly understood, limiting our ability to interpret, improve, and…

Machine Learning · Computer Science 2025-06-16 Chengye Li , Haiyun Liu , Yuanxi Li

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

In real-world NLP applications, Large Language Models (LLMs) offer promising solutions due to their extensive training on vast datasets. However, the large size and high computation demands of LLMs limit their practicality in many…

Artificial Intelligence · Computer Science 2025-04-01 Juanhui Li , Sreyashi Nag , Hui Liu , Xianfeng Tang , Sheikh Sarwar , Limeng Cui , Hansu Gu , Suhang Wang , Qi He , Jiliang Tang

Knowledge Distillation (KD) is a model-agnostic technique to improve model quality while having a fixed capacity budget. It is a commonly used technique for model compression, where a larger capacity teacher model with better quality is…

Machine Learning · Computer Science 2021-03-02 Jiaxi Tang , Rakesh Shivanna , Zhe Zhao , Dong Lin , Anima Singh , Ed H. Chi , Sagar Jain

Knowledge distillation aims to learn a lightweight student network from a pre-trained teacher network. In practice, existing knowledge distillation methods are usually infeasible when the original training data is unavailable due to some…

Computer Vision and Pattern Recognition · Computer Science 2023-07-24 Jialiang Tang , Shuo Chen , Gang Niu , Masashi Sugiyama , Chen Gong

Distillation is an effective knowledge-transfer technique that uses predicted distributions of a powerful teacher model as soft targets to train a less-parameterized student model. A pre-trained high capacity teacher, however, is not always…

Machine Learning · Computer Science 2019-12-06 Defang Chen , Jian-Ping Mei , Can Wang , Yan Feng , Chun Chen

In this work, we propose Mutual Information Maximization Knowledge Distillation (MIMKD). Our method uses a contrastive objective to simultaneously estimate and maximize a lower bound on the mutual information of local and global feature…

Computer Vision and Pattern Recognition · Computer Science 2023-05-12 Aman Shrivastava , Yanjun Qi , Vicente Ordonez

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 is initially introduced to utilize additional supervision from a single teacher model for the student model training. To boost the student performance, some recent variants attempt to exploit diverse knowledge sources…

Machine Learning · Computer Science 2022-02-15 Hailin Zhang , Defang Chen , Can Wang

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