English
Related papers

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

200 papers

On-policy distillation (OPD) trains a student on its own rollouts with token-level teacher supervision. Recent selective OPD methods exploit the non-uniformity of OPD signals by prioritizing high-entropy or high-disagreement tokens. We…

Machine Learning · Computer Science 2026-05-27 Yuanyi Wang , Su Lu , Yanggan Gu , Pengkai Wang , Yifan Yang , Zhaoyi Yan , Congkai Xie , Jianmin Wu , Hongxia Yang

Knowledge Distillation (KD), a learning manner with a larger teacher network guiding a smaller student network, transfers dark knowledge from the teacher to the student via logits or intermediate features, with the aim of producing a…

Machine Learning · Computer Science 2024-12-04 Chengting Yu , Fengzhao Zhang , Ruizhe Chen , Aili Wang , Zuozhu Liu , Shurun Tan , Er-Ping Li

Knowledge distillation aims to enhance the performance of a lightweight student model by exploiting the knowledge from a pre-trained cumbersome teacher model. However, in the traditional knowledge distillation, teacher predictions are only…

Machine Learning · Computer Science 2023-05-26 Shiya Luo , Defang Chen , Can Wang

Recently, large-scale pre-trained models have shown their advantages in many tasks. However, due to the huge computational complexity and storage requirements, it is challenging to apply the large-scale model to real scenes. A common…

Computer Vision and Pattern Recognition · Computer Science 2022-12-27 Deng Li , Aming Wu , Yahong Han , Qi Tian

Several methods of knowledge distillation have been developed for neural network compression. While they all use the KL divergence loss to align the soft outputs of the student model more closely with that of the teacher, the various…

Computer Vision and Pattern Recognition · Computer Science 2020-12-08 Huan Wang , Suhas Lohit , Michael Jones , Yun Fu

Despite the success of distillation in large language models (LLMs), most prior work applies identical loss functions to both teacher- and student-generated data. These strategies overlook the synergy between loss formulations and data…

Computation and Language · Computer Science 2025-06-02 Jongwoo Ko , Tianyi Chen , Sungnyun Kim , Tianyu Ding , Luming Liang , Ilya Zharkov , Se-Young Yun

Recent advances in knowledge distillation (KD) have enabled smaller student models to approach the performance of larger teacher models. However, popular methods such as supervised KD and on-policy KD, are adversely impacted by the…

Computation and Language · Computer Science 2025-04-29 Wenda Xu , Rujun Han , Zifeng Wang , Long T. Le , Dhruv Madeka , Lei Li , William Yang Wang , Rishabh Agarwal , Chen-Yu Lee , Tomas Pfister

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

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

This paper addresses the challenges of high computational cost and slow inference in deploying large language models. It proposes a distillation strategy guided by multiple teacher models. The method constructs several teacher models and…

Computation and Language · Computer Science 2025-07-22 Xiandong Meng , Yan Wu , Yexin Tian , Xin Hu , Tianze Kang , Junliang Du

Reinforcement learning (RL) post-training has recently driven major gains in long chain-of-thought reasoning large language models (LLMs), but the high inference cost of such models motivates distillation into smaller students. Most…

Machine Learning · Computer Science 2026-04-13 Zhaoyang Zhang , Shuli Jiang , Yantao Shen , Yuting Zhang , Dhananjay Ram , Shuo Yang , Zhuowen Tu , Wei Xia , Stefano Soatto

Representation learning has been evolving from traditional supervised training to Contrastive Learning (CL) and Masked Image Modeling (MIM). Previous works have demonstrated their pros and cons in specific scenarios, i.e., CL and supervised…

Computer Vision and Pattern Recognition · Computer Science 2023-06-29 Bowen Shi , Xiaopeng Zhang , Yaoming Wang , Jin Li , Wenrui Dai , Junni Zou , Hongkai Xiong , Qi Tian

Recent advances in deep learning has lead to rapid developments in the field of image retrieval. However, the best performing architectures incur significant computational cost. Recent approaches tackle this issue using knowledge…

Computer Vision and Pattern Recognition · Computer Science 2020-07-14 Zakaria Laskar , Juho Kannala

Dominant dual-encoder models enable efficient image-text retrieval but suffer from limited accuracy while the cross-encoder models offer higher accuracy at the expense of efficiency. Distilling cross-modality matching knowledge from…

Computer Vision and Pattern Recognition · Computer Science 2024-07-11 Yuxin Chen , Zongyang Ma , Ziqi Zhang , Zhongang Qi , Chunfeng Yuan , Bing Li , Junfu Pu , Ying Shan , Xiaojuan Qi , Weiming Hu

While knowledge distillation has seen widespread use in pre-training and instruction tuning, its application to aligning language models with human preferences remains underexplored, particularly in the more realistic cross-tokenizer…

Computation and Language · Computer Science 2026-01-21 Truong Nguyen , Phi Van Dat , Ngan Nguyen , Linh Ngo Van , Trung Le , Thanh Hong Nguyen

Knowledge distillation transfers knowledge from a large model to a small one via task and distillation losses. In this paper, we observe a trade-off between task and distillation losses, i.e., introducing distillation loss limits the…

Computer Vision and Pattern Recognition · Computer Science 2023-07-18 Borui Zhao , Quan Cui , Renjie Song , Jiajun Liang

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 (KD) is an effective framework for compressing deep learning models, realized by a student-teacher paradigm requiring small student networks to mimic the soft target generated by well-trained teachers. However, the…

Computer Vision and Pattern Recognition · Computer Science 2020-05-20 Yuang Liu , Wei Zhang , Jun Wang

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

Vision-language models (VLMs) have achieved remarkable success across multimodal tasks, yet their substantial computational demands hinder efficient deployment. Knowledge distillation (KD) has emerged as a powerful approach for building…

Computer Vision and Pattern Recognition · Computer Science 2025-11-25 Pume Tuchinda , Parinthapat Pengpun , Romrawin Chumpu , Sarana Nutanong , Peerat Limkonchotiwat