English
Related papers

Related papers: Dynamic Self-Distillation via Previous Mini-batche…

200 papers

Knowledge distillation has emerged as an effective strategy for compressing large language models' (LLMs) knowledge into smaller, more efficient student models. However, standard one-shot distillation methods often produce suboptimal…

Computation and Language · Computer Science 2025-04-04 Kushal Jain , Piyushi Goyal , Kumar Shridhar

Although deep learning models owe their remarkable success to deep and complex architectures, this very complexity typically comes at the expense of real-time performance. To address this issue, a variety of model compression techniques…

Machine Learning · Computer Science 2025-05-13 Seongmin Kim , Kwanho Kim , Minseung Kim , Kanghyun Jo

Existing techniques often attempt to make knowledge transfer from a powerful machine translation (MT) to speech translation (ST) model with some elaborate techniques, which often requires transcription as extra input during training.…

Computation and Language · Computer Science 2023-04-21 Hao Zhang , Nianwen Si , Yaqi Chen , Wenlin Zhang , Xukui Yang , Dan Qu , Zhen Li

In recent years, large language models (LLMs) have shown exceptional capabilities across various natural language processing (NLP) tasks. However, such impressive performance often comes with the trade-off of an increased parameter size,…

Computation and Language · Computer Science 2025-02-19 Minchong Li , Feng Zhou , Xiaohui Song

Knowledge distillation (KD) is a highly promising method for mitigating the computational problems of pre-trained language models (PLMs). Among various KD approaches, Intermediate Layer Distillation (ILD) has been a de facto standard KD…

Computation and Language · Computer Science 2023-02-06 Jongwoo Ko , Seungjoon Park , Minchan Jeong , Sukjin Hong , Euijai Ahn , Du-Seong Chang , Se-Young Yun

In natural language processing (NLP) tasks, slow inference speed and huge footprints in GPU usage remain the bottleneck of applying pre-trained deep models in production. As a popular method for model compression, knowledge distillation…

Computation and Language · Computer Science 2020-12-15 Fei Yuan , Linjun Shou , Jian Pei , Wutao Lin , Ming Gong , Yan Fu , Daxin Jiang

Large Language Models (LLMs) face significant challenges at inference time due to their high computational demands. To address this, we present Performance-Guided Knowledge Distillation (PGKD), a cost-effective and high-throughput solution…

Computation and Language · Computer Science 2024-11-11 Flavio Di Palo , Prateek Singhi , Bilal Fadlallah

Knowledge distillation (KD) is a widely adopted approach for compressing large neural networks by transferring knowledge from a large teacher model to a smaller student model. In the context of large language models, token level KD,…

Computation and Language · Computer Science 2025-09-19 Yihan Cao , Yanbin Kang , Zhengming Xing , Ruijie Jiang

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

Incremental language learning with pseudo-data can alleviate catastrophic forgetting in neural networks. However, to obtain better performance, former methods have higher demands for pseudo-data of the previous tasks. The performance…

Computation and Language · Computer Science 2021-10-19 Han Wang , Ruiliu Fu , Chengzhang Li , Xuejun Zhang , Jun Zhou , Yonghong Yan

Large language models (LLMs) achieve strong performance but remain costly to deploy in resource-constrained settings. Training small language models (SLMs) from scratch is computationally expensive, while conventional knowledge distillation…

Computation and Language · Computer Science 2026-05-11 Boyu Shi , YiCheng Jiang , Chang Liu , Qiufeng Wang , Xu Yang , Xin Geng

Knowledge Distillation (KD) is a widely used technique to transfer knowledge from pre-trained teacher models to (usually more lightweight) student models. However, in certain situations, this technique is more of a curse than a blessing.…

Machine Learning · Computer Science 2021-05-18 Haoyu Ma , Tianlong Chen , Ting-Kuei Hu , Chenyu You , Xiaohui Xie , Zhangyang Wang

We study semi-supervised sequence generation tasks, where the few labeled examples are too scarce to finetune a model, and meanwhile, few-shot prompted large language models (LLMs) exhibit room for improvement. In this paper, we present the…

Computation and Language · Computer Science 2024-08-06 Jiachen Zhao , Wenlong Zhao , Andrew Drozdov , Benjamin Rozonoyer , Md Arafat Sultan , Jay-Yoon Lee , Mohit Iyyer , Andrew McCallum

Knowledge Distillation (KD) compresses large language models (LLMs) by transferring the teacher model's capabilities to a smaller student model, reducing inference cost and memory usage while maintaining performance. However, existing KD…

Computation and Language · Computer Science 2025-06-11 Lingyuan Liu , Mengxiang Zhang

Knowledge Distillation (KD) transfers knowledge from a large teacher model to a smaller student by aligning their predictive distributions. However, conventional KD formulations - typically based on Kullback-Leibler divergence - assume that…

Machine Learning · Computer Science 2026-02-05 Ondrej Tybl , Lukas Neumann

How can we efficiently compress a model while maintaining its performance? Knowledge Distillation (KD) is one of the widely known methods for model compression. In essence, KD trains a smaller student model based on a larger teacher model…

Machine Learning · Computer Science 2020-12-14 Ikhyun Cho , U Kang

Knowledge distillation (KD) is a successful approach for deep neural network acceleration, with which a compact network (student) is trained by mimicking the softmax output of a pre-trained high-capacity network (teacher). In tradition, KD…

Machine Learning · Computer Science 2021-06-08 Zi Wang

Knowledge distillation (KD) is an effective model compression technique where a compact student network is taught to mimic the behavior of a complex and highly trained teacher network. In contrast, Mutual Learning (ML) provides an…

Computer Vision and Pattern Recognition · Computer Science 2021-10-25 Usma Niyaz , Deepti R. Bathula

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 (KD) has emerged as a promising technique for addressing the computational challenges associated with deploying large-scale recommender systems. KD transfers the knowledge of a massive teacher system to a compact…

Information Retrieval · Computer Science 2024-06-27 Gyuseok Lee , SeongKu Kang , Wonbin Kweon , Hwanjo Yu