English
Related papers

Related papers: Don't Ignore the Tail: Decoupling top-K Probabilit…

200 papers

Spiking Neural Networks (SNNs) have emerged as a promising approach for energy-efficient and biologically plausible computation. However, due to limitations in existing training methods and inherent model constraints, SNNs often exhibit a…

Artificial Intelligence · Computer Science 2025-05-19 Tianqing Zhang , Zixin Zhu , Kairong Yu , Hongwei Wang

Knowledge distillation is widely used to improve generalization in practice, yet its theoretical understanding remains elusive. In the standard distillation setting, a teacher model provides soft predictions to guide the training of a…

Information Theory · Computer Science 2026-05-18 Bingying Li , Haiyun He

Conventional knowledge distillation, designed for model compression, fails on long-tailed distributions because the teacher model tends to be biased toward head classes and provides limited supervision for tail classes. We propose…

Computer Vision and Pattern Recognition · Computer Science 2026-03-02 Seonghak Kim

Reverse Kullback-Leibler (RKL) divergence has recently emerged as the preferred objective for large language model (LLM) distillation, consistently outperforming forward KL (FKL), particularly in regimes with large vocabularies and…

Machine Learning · Computer Science 2026-04-02 Hoang-Chau Luong , Dat Ba Tran , Lingwei Chen

Knowledge distillation (KD), transferring knowledge from a cumbersome teacher model to a lightweight student model, has been investigated to design efficient neural architectures. Generally, the objective function of KD is the…

Machine Learning · Computer Science 2021-05-20 Taehyeon Kim , Jaehoon Oh , NakYil Kim , Sangwook Cho , Se-Young Yun

Knowledge distillation involves transferring knowledge from large, cumbersome teacher models to more compact student models. The standard approach minimizes the Kullback-Leibler (KL) divergence between the probabilistic outputs of a teacher…

Computer Vision and Pattern Recognition · Computer Science 2025-05-14 Nikolaos Giakoumoglou , Tania Stathaki

Unlike existing knowledge distillation methods focus on the baseline settings, where the teacher models and training strategies are not that strong and competing as state-of-the-art approaches, this paper presents a method dubbed DIST to…

Computer Vision and Pattern Recognition · Computer Science 2022-12-29 Tao Huang , Shan You , Fei Wang , Chen Qian , Chang Xu

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

Knowledge distillation typically minimizes the Kullback-Leibler (KL) divergence between teacher and student logits. However, optimizing the KL divergence can be challenging for the student and often leads to sub-optimal solutions. We…

Computer Vision and Pattern Recognition · Computer Science 2025-06-17 Yuchen Guan , Runxi Cheng , Kang Liu , Chun Yuan

Knowledge distillation (KD) is widely used for compressing a teacher model to a smaller student model, reducing its inference cost and memory footprint while preserving model capabilities. However, current KD methods for auto-regressive…

Computation and Language · Computer Science 2024-07-04 Jongwoo Ko , Sungnyun Kim , Tianyi Chen , Se-Young Yun

Large language models (LLMs) have significantly advanced various natural language processing tasks, but deploying them remains computationally expensive. Knowledge distillation (KD) is a promising solution, enabling the transfer of…

Computation and Language · Computer Science 2024-10-22 Yuhang Zhou , Jing Zhu , Paiheng Xu , Xiaoyu Liu , Xiyao Wang , Danai Koutra , Wei Ai , Furong Huang

Knowledge distillation (KD) is an effective model compression method that can transfer the internal capabilities of large language models (LLMs) to smaller ones. However, the multi-modal probability distribution predicted by teacher LLMs…

Computation and Language · Computer Science 2024-12-19 Tianyu Peng , Jiajun Zhang

The widespread deployment of Large Language Models (LLMs) is hindered by the high computational demands, making knowledge distillation (KD) crucial for developing compact smaller ones. However, the conventional KD methods endure the…

Computation and Language · Computer Science 2025-02-18 Zengkui Sun , Yijin Liu , Fandong Meng , Yufeng Chen , Jinan Xu , Jie Zhou

Deep models trained on long-tailed datasets exhibit unsatisfactory performance on tail classes. Existing methods usually modify the classification loss to increase the learning focus on tail classes, which unexpectedly sacrifice the…

Computer Vision and Pattern Recognition · Computer Science 2021-04-22 Shaoyu Zhang , Chen Chen , Xiyuan Hu , Silong Peng

The improvement in the performance of efficient and lightweight models (i.e., the student model) is achieved through knowledge distillation (KD), which involves transferring knowledge from more complex models (i.e., the teacher model).…

Computer Vision and Pattern Recognition · Computer Science 2025-05-20 Seonghak Kim , Gyeongdo Ham , Yucheol Cho , Daeshik Kim

Knowledge Distillation (KD) transfers knowledge from a large pre-trained teacher network to a compact and efficient student network, making it suitable for deployment on resource-limited media terminals. However, traditional KD methods…

Computer Vision and Pattern Recognition · Computer Science 2024-09-23 Xinlei Huang , Jialiang Tang , Xubin Zheng , Jinjia Zhou , Wenxin Yu , Ning Jiang

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

Knowledge distillation has been widely adopted in computer vision task processing, since it can effectively enhance the performance of lightweight student networks by leveraging the knowledge transferred from cumbersome teacher networks.…

Computer Vision and Pattern Recognition · Computer Science 2025-01-15 Yafei Qi , Chen Wang , Zhaoning Zhang , Yaping Liu , Yongmin Zhang

Knowledge distillation (KD) is a promising technique for model compression in neural machine translation. However, where the knowledge hides in KD is still not clear, which may hinder the development of KD. In this work, we first unravel…

Computation and Language · Computer Science 2024-07-18 Songming Zhang , Yunlong Liang , Shuaibo Wang , Wenjuan Han , Jian Liu , Jinan Xu , Yufeng Chen

In the history of knowledge distillation, the focus has once shifted over time from logit-based to feature-based approaches. However, this transition has been revisited with the advent of Decoupled Knowledge Distillation (DKD), which…

Machine Learning · Computer Science 2025-12-05 Bowen Zheng , Ran Cheng
‹ Prev 1 2 3 10 Next ›