English
Related papers

Related papers: Knowledge Distillation from Non-streaming to Strea…

200 papers

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

We present a novel adversarial penalized self-knowledge distillation method, named adversarial learning and implicit regularization for self-knowledge distillation (AI-KD), which regularizes the training procedure by adversarial learning…

Computer Vision and Pattern Recognition · Computer Science 2024-03-22 Hyungmin Kim , Sungho Suh , Sunghyun Baek , Daehwan Kim , Daun Jeong , Hansang Cho , Junmo Kim

Knowledge distillation (KD) is a technique to derive optimal performance from a small student network (SN) by distilling knowledge of a large teacher network (TN) and transferring the distilled knowledge to the small SN. Since a role of…

Machine Learning · Computer Science 2019-07-10 Seunghyun Lee , Byung Cheol Song

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) involves transferring knowledge from a pre-trained heavy teacher model to a lighter student model, thereby reducing the inference cost while maintaining comparable effectiveness. Prior KD techniques typically…

Computer Vision and Pattern Recognition · Computer Science 2025-10-17 Jhe-Hao Lin , Yi Yao , Chan-Feng Hsu , Hongxia Xie , Hong-Han Shuai , Wen-Huang Cheng

Knowledge distillation (KD) is a standard route to compress Large Language Models (LLMs) into compact students, yet most pipelines uniformly apply token-wise loss regardless of teacher confidence. This indiscriminate supervision amplifies…

Computation and Language · Computer Science 2025-11-18 Haiduo Huang , Jiangcheng Song , Yadong Zhang , Pengju Ren

End-to-end automatic speech recognition (ASR), unlike conventional ASR, does not have modules to learn the semantic representation from speech encoder. Moreover, the higher frame-rate of speech representation prevents the model to learn the…

Artificial Intelligence · Computer Science 2021-03-19 Md Akmal Haidar , Chao Xing , Mehdi Rezagholizadeh

Pre-trained language models (PLMs) have emerged as powerful tools for code understanding. However, deploying these PLMs in large-scale applications faces practical challenges due to their computational intensity and inference latency.…

Software Engineering · Computer Science 2025-08-22 Ruiqi Wang , Zezhou Yang , Cuiyun Gao , Xin Xia , Qing Liao

Recently, the advance in deep learning has brought a considerable improvement in the end-to-end speech recognition field, simplifying the traditional pipeline while producing promising results. Among the end-to-end models, the connectionist…

Audio and Speech Processing · Electrical Eng. & Systems 2022-11-29 Ji Won Yoon , Beom Jun Woo , Sunghwan Ahn , Hyeonseung Lee , Nam Soo Kim

We present Knowledge Distillation with Meta Learning (MetaDistil), a simple yet effective alternative to traditional knowledge distillation (KD) methods where the teacher model is fixed during training. We show the teacher network can learn…

Machine Learning · Computer Science 2022-04-05 Wangchunshu Zhou , Canwen Xu , Julian McAuley

Speculative Decoding (SD) accelerates large language model inference by employing a small draft model to generate predictions, which are then verified by a larger target model. The effectiveness of SD hinges on the alignment between these…

Computation and Language · Computer Science 2025-10-23 Yuezhou Hu , Jiaxin Guo , Xinyu Feng , Tuo Zhao

Multilingual speech data often suffer from long-tailed language distribution, resulting in performance degradation. However, multilingual text data is much easier to obtain, yielding a more useful general language model. Hence, we are…

Computation and Language · Computer Science 2022-06-28 Kwanghee Choi , Hyung-Min Park

Knowledge distillation field delicately designs various types of knowledge to shrink the performance gap between compact student and large-scale teacher. These existing distillation approaches simply focus on the improvement of…

Computer Vision and Pattern Recognition · Computer Science 2021-09-28 Xuanyang Zhang , Xiangyu Zhang , Jian Sun

With the rapid development of artificial intelligence (AI), especially in the medical field, the need for its explainability has grown. In medical image analysis, a high degree of transparency and model interpretability can help clinicians…

Artificial Intelligence · Computer Science 2025-02-25 Yuchen Jiang , Xinyuan Zhao , Yihang Wu , Ahmad Chaddad

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

Due to privacy or patent concerns, a growing number of large models are released without granting access to their training data, making transferring their knowledge inefficient and problematic. In response, Data-Free Knowledge Distillation…

Machine Learning · Computer Science 2024-03-19 Zihao Tang , Zheqi Lv , Shengyu Zhang , Yifan Zhou , Xinyu Duan , Fei Wu , Kun Kuang

We propose a simple yet effective method to compress an RNN-Transducer (RNN-T) through the well-known knowledge distillation paradigm. We show that the transducer's encoder outputs naturally have a high entropy and contain rich information…

Computation and Language · Computer Science 2021-06-16 Rupak Vignesh Swaminathan , Brian King , Grant P. Strimel , Jasha Droppo , Athanasios Mouchtaris

Knowledge distillation (KD) is a valuable technique for compressing large deep learning models into smaller, edge-suitable networks. However, conventional KD frameworks rely on pre-trained high-capacity teacher networks, which introduce…

Computer Vision and Pattern Recognition · Computer Science 2025-05-21 Hongjun Choi , Eun Som Jeon , Ankita Shukla , Pavan Turaga

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

Knowledge distillation (KD) is a key technique for compressing large language models into smaller ones while preserving performance. Despite the recent traction of KD research, its effectiveness for smaller language models (LMs) and the…

Computation and Language · Computer Science 2025-08-05 Suhas Kamasetty Ramesh , Ayan Sengupta , Tanmoy Chakraborty