English
Related papers

Related papers: X-Token: Projection-Guided Cross-Tokenizer Knowled…

200 papers

Recent research on knowledge distillation has increasingly focused on logit distillation because of its simplicity, effectiveness, and versatility in model compression. In this paper, we introduce Refined Logit Distillation (RLD) to address…

Computer Vision and Pattern Recognition · Computer Science 2025-07-29 Wujie Sun , Defang Chen , Siwei Lyu , Genlang Chen , Chun Chen , Can Wang

Knowledge distillation (KD) is an established paradigm for transferring privileged knowledge from a cumbersome model to a lightweight and efficient one. In recent years, logit-based KD methods are quickly catching up in performance with…

Computer Vision and Pattern Recognition · Computer Science 2024-12-24 Weijia Zhang , Dongnan Liu , Weidong Cai , Chao Ma

Knowledge distillation (KD) aims to distill the knowledge from the teacher (larger) to the student (smaller) model via soft-label for the efficient neural network. In general, the performance of a model is determined by accuracy, which is…

Signal Processing · Electrical Eng. & Systems 2025-08-25 Stephen Ekaputra Limantoro

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

Knowledge distillation from large language models (LLMs) assumes that the teacher's output distribution is a high-quality training signal. On reasoning tasks, this assumption is frequently violated. A model's intermediate representations…

Computation and Language · Computer Science 2026-03-16 Ryan Brown , Chris Russell

Knowledge distillation can be a cost-effective technique to distill knowledge in Large Language Models, if the teacher output logits can be pre-computed and cached. However, successfully applying this to pre-training remains largely…

Machine Learning · Computer Science 2025-07-25 Anshumann , Mohd Abbas Zaidi , Akhil Kedia , Jinwoo Ahn , Taehwak Kwon , Kangwook Lee , Haejun Lee , Joohyung Lee

Knowledge distillation, transferring knowledge from a teacher model to a student model, has emerged as a powerful technique in neural machine translation for compressing models or simplifying training targets. Knowledge distillation…

Computation and Language · Computer Science 2024-04-24 Jingxuan Wei , Linzhuang Sun , Yichong Leng , Xu Tan , Bihui Yu , Ruifeng Guo

In this paper, we propose a novel method, X-Distill, to improve the self-supervised training of monocular depth via cross-task knowledge distillation from semantic segmentation to depth estimation. More specifically, during training, we…

Computer Vision and Pattern Recognition · Computer Science 2021-10-26 Hong Cai , Janarbek Matai , Shubhankar Borse , Yizhe Zhang , Amin Ansari , Fatih Porikli

Knowledge Distillation (KD) has emerged as a crucial technique for compressing Large Language Models (LLMs). Although existing cross-tokenizer KD methods have made notable progress, their effectiveness remains constrained by suboptimal…

Computation and Language · Computer Science 2026-02-26 Duc Trung Vu , Pham Khanh Chi , Dat Phi Van , Linh Ngo Van , Sang Dinh , Trung Le

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

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

Knowledge distillation (KD)transfers the dark knowledge from a complex teacher to a compact student. However, heterogeneous architecture distillation, such as Vision Transformer (ViT) to ResNet18, faces challenges due to differences in…

Computer Vision and Pattern Recognition · Computer Science 2026-02-16 Liuchi Xu , Hao Zheng , Lu Wang , Lisheng Xu , Jun Cheng

There is increasing interest in distilling task-specific knowledge from large language models (LLM) to smaller student models. Nonetheless, LLM distillation presents a dual challenge: 1) there is a high cost associated with querying the…

Computation and Language · Computer Science 2024-06-11 Yuhang Zhou , Wei Ai

Knowledge distillation aims to transfer knowledge to the student model by utilizing the predictions/features of the teacher model, and feature-based distillation has recently shown its superiority over logit-based distillation. However, due…

Computer Vision and Pattern Recognition · Computer Science 2022-11-29 Shuoxi Zhang , Hanpeng Liu , John E. Hopcroft , Kun He

Knowledge distillation (KD) has shown great promise in transferring knowledge from larger teacher models to smaller student models. However, existing KD strategies for large language models often minimize output distributions between…

Computation and Language · Computer Science 2024-12-23 Yuncheng Song , Liang Ding , Changtong Zan , Shujian Huang

Knowledge distillation (KD) is a promising solution to compress large language models (LLMs) by transferring their knowledge to smaller models. During this process, white-box KD methods usually minimize the distance between the output…

Computation and Language · Computer Science 2025-04-16 Xue Zhang , Songming Zhang , Yunlong Liang , Fandong Meng , Yufeng Chen , Jinan Xu , Jie Zhou

Knowledge Distillation (KD) is a critical tool for training Large Language Models (LLMs), yet the majority of research focuses on approaches that rely solely on output logits, neglecting semantic information in the teacher's intermediate…

Computation and Language · Computer Science 2026-05-13 Maxime Guigon , Lucas Dixon , Michaël E. Sander

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

Generative Language Models (GLMs) have shown impressive performance in tasks such as text generation, understanding, and reasoning. However, the large model size poses challenges for practical deployment. To solve this problem,…

Computation and Language · Computer Science 2023-12-05 Minsoo Kim , Sihwa Lee , Janghwan Lee , Sukjin Hong , Du-Seong Chang , Wonyong Sung , Jungwook Choi

Knowledge distillation (KD) methods can transfer knowledge of a parameter-heavy teacher model to a light-weight student model. The status quo for feature KD methods is to utilize loss functions based on logits (i.e., pre-softmax class…

Computer Vision and Pattern Recognition · Computer Science 2025-11-20 Nicholas Cooper , Lijun Chen , Sailesh Dwivedy , Danna Gurari