English
Related papers

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

200 papers

With ever growing scale of neural models, knowledge distillation (KD) attracts more attention as a prominent tool for neural model compression. However, there are counter intuitive observations in the literature showing some challenging…

Computation and Language · Computer Science 2021-10-19 Mehdi Rezagholizadeh , Aref Jafari , Puneeth Salad , Pranav Sharma , Ali Saheb Pasand , Ali Ghodsi

Knowledge distillation addresses the problem of transferring knowledge from a teacher model to a student model. In this process, we typically have multiple types of knowledge extracted from the teacher model. The problem is to make full use…

Computation and Language · Computer Science 2023-02-02 Chenglong Wang , Yi Lu , Yongyu Mu , Yimin Hu , Tong Xiao , Jingbo Zhu

On-policy distillation (OPD) is a standard tool for transferring teacher behavior to a smaller student, but it implicitly assumes that teacher and student predictions are comparable token by token, an assumption that fails whenever the two…

Computation and Language · Computer Science 2026-05-22 Jie Sun , Mao Zheng , Mingyang Song , Qiyong Zhong , Yilin Cheng , Bichuan Feng , Pengfei Liu , Junfeng Fang , Xiang Wang

Knowledge distillation is a popular technique for training a small student network to emulate a larger teacher model, such as an ensemble of networks. We show that while knowledge distillation can improve student generalization, it does not…

Machine Learning · Computer Science 2021-12-07 Samuel Stanton , Pavel Izmailov , Polina Kirichenko , Alexander A. Alemi , Andrew Gordon Wilson

Multi-task learning (MTL) is to learn one single model that performs multiple tasks for achieving good performance on all tasks and lower cost on computation. Learning such a model requires to jointly optimize losses of a set of tasks with…

Computer Vision and Pattern Recognition · Computer Science 2020-09-25 Wei-Hong Li , Hakan Bilen

We propose a resource-efficient framework for compressing large language models through knowledge distillation, combined with guided chain-of-thought reinforcement learning. Using Qwen 3B as the teacher and Qwen 0.5B as the student, we…

Computation and Language · Computer Science 2026-03-17 Alejandro Paredes La Torre , Barbara Flores , Diego Rodriguez

Vision Language Models (VLMs), pre-trained on large-scale image-text datasets, enable zero-shot predictions for unseen data but may underperform on specific unseen tasks. Continual learning (CL) can help VLMs effectively adapt to new data…

Computer Vision and Pattern Recognition · Computer Science 2024-11-12 Hongsheng Zhang , Zhong Ji , Jingren Liu , Yanwei Pang , Jungong Han

In the knowledge distillation literature, feature-based methods have dominated due to their ability to effectively tap into extensive teacher models. In contrast, logit-based approaches, which aim to distill "dark knowledge" from teachers,…

Computer Vision and Pattern Recognition · Computer Science 2025-08-06 Md. Ismail Hossain , M M Lutfe Elahi , Sameera Ramasinghe , Ali Cheraghian , Fuad Rahman , Nabeel Mohammed , Shafin Rahman

Knowledge Distillation (KD) aims at improving the performance of a low-capacity student model by inheriting knowledge from a high-capacity teacher model. Previous KD methods typically train a student by minimizing a task-related loss and…

Computer Vision and Pattern Recognition · Computer Science 2019-09-10 Mengya Gao , Yujun Shen , Quanquan Li , Junjie Yan , Liang Wan , Dahua Lin , Chen Change Loy , Xiaoou Tang

Knowledge distillation (KD) is a key technique for compressing large-scale language models (LLMs), yet prevailing logit-based methods typically employ static strategies that are misaligned with the dynamic learning process of student…

Computation and Language · Computer Science 2025-10-14 Xurong Xie , Zhucun Xue , Jiafu Wu , Jian Li , Yabiao Wang , Xiaobin Hu , Yong Liu , Jiangning Zhang

Temporal knowledge graphs (TKGs) support reasoning over time-evolving facts, yet state-of-the-art models are often computationally heavy and costly to deploy. Existing compression and distillation techniques are largely designed for static…

Computation and Language · Computer Science 2026-02-17 Wang Xing , Wei Song , Siyu Lin , Chen Wu , Man Wang

Knowledge distillation (KD) is a common approach to compress a teacher model to reduce its inference cost and memory footprint, by training a smaller student model. However, in the context of autoregressive language models (LMs), we…

Computation and Language · Computer Science 2024-06-18 Qihuang Zhong , Liang Ding , Li Shen , Juhua Liu , Bo Du , Dacheng Tao

Knowledge distillation (KD) is an efficient approach to transfer the knowledge from a large "teacher" network to a smaller "student" network. Traditional KD methods require lots of labeled training samples and a white-box teacher…

Computer Vision and Pattern Recognition · Computer Science 2022-07-26 Dang Nguyen , Sunil Gupta , Kien Do , Svetha Venkatesh

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

Existing knowledge distillation methods typically work by imparting the knowledge of output logits or intermediate feature maps from the teacher network to the student network, which is very successful in multi-class single-label learning.…

Machine Learning · Computer Science 2025-06-02 Penghui Yang , Ming-Kun Xie , Chen-Chen Zong , Lei Feng , Gang Niu , Masashi Sugiyama , Sheng-Jun Huang

Knowledge Distillation (KD) for Large Language Models (LLMs) has become increasingly important as models grow in size and complexity. While existing distillation approaches focus on imitating teacher behavior, they often overlook the…

Computation and Language · Computer Science 2026-02-16 Yuang Cai , Yuyu Yuan

Pretrained language models have led to significant performance gains in many NLP tasks. However, the intensive computing resources to train such models remain an issue. Knowledge distillation alleviates this problem by learning a…

Computation and Language · Computer Science 2020-05-04 Linqing Liu , Huan Wang , Jimmy Lin , Richard Socher , Caiming Xiong

Knowledge distillation is a widely applicable technique for training a student neural network under the guidance of a trained teacher network. For example, in neural network compression, a high-capacity teacher is distilled to train a…

Computer Vision and Pattern Recognition · Computer Science 2019-08-05 Frederick Tung , Greg Mori

Deep neural models in recent years have been successful in almost every field, including extremely complex problem statements. However, these models are huge in size, with millions (and even billions) of parameters, thus demanding more…

Computer Vision and Pattern Recognition · Computer Science 2021-06-18 Lin Wang , Kuk-Jin Yoon

Despite the impressive performance achieved by data-fusion networks with duplex encoders for visual semantic segmentation, they become ineffective when spatial geometric data are not available. Implicitly infusing the spatial geometric…

Computer Vision and Pattern Recognition · Computer Science 2025-03-17 Sicen Guo , Ziwei Long , Zhiyuan Wu , Qijun Chen , Ioannis Pitas , Rui Fan