English
Related papers

Related papers: AdaSPEC: Selective Knowledge Distillation for Effi…

200 papers

Prior work has shown that, on small amounts of training data, syntactic neural language models learn structurally sensitive generalisations more successfully than sequential language models. However, their computational complexity renders…

Computation and Language · Computer Science 2019-06-18 Adhiguna Kuncoro , Chris Dyer , Laura Rimell , Stephen Clark , Phil Blunsom

Knowledge Distillation (KD) is a powerful technique for transferring knowledge between neural network models, where a pre-trained teacher model is used to facilitate the training of the target student model. However, the availability of a…

Computer Vision and Pattern Recognition · Computer Science 2023-05-17 Xucong Wang , Pengchao Han , Lei Guo

Speculative decoding (SD) accelerates Large Language Model (LLM) generation by using an efficient draft model to propose the next few tokens, which are verified by the LLM in a single forward call, reducing latency while preserving its…

Computation and Language · Computer Science 2025-05-30 Milan Gritta , Huiyin Xue , Gerasimos Lampouras

The advent of scalable deep models and large datasets has improved the performance of Neural Machine Translation. Knowledge Distillation (KD) enhances efficiency by transferring knowledge from a teacher model to a more compact student…

Computation and Language · Computer Science 2024-03-26 Heegon Jin , Seonil Son , Jemin Park , Youngseok Kim , Hyungjong Noh , Yeonsoo Lee

Deployment of autoregressive large language models (LLMs) is costly, and as these models increase in size, the associated costs will become even more considerable. Consequently, different methods have been proposed to accelerate the token…

Computation and Language · Computer Science 2024-07-03 Parsa Kavehzadeh , Mohammadreza Pourreza , Mojtaba Valipour , Tinashu Zhu , Haoli Bai , Ali Ghodsi , Boxing Chen , Mehdi Rezagholizadeh

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

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

Reasoning distillation has emerged as a prevailing paradigm for transferring reasoning capabilities from large reasoning models to small language models. Yet, reasoning distillation risks data contamination: benchmark data may inadvertently…

Computation and Language · Computer Science 2026-05-11 Hengxiang Zhang , Hyeong Kyu Choi , Sharon Li , Hongxin Wei

Several recent studies have elucidated why knowledge distillation (KD) improves model performance. However, few have researched the other advantages of KD in addition to its improving model performance. In this study, we have attempted to…

Machine Learning · Computer Science 2023-05-26 Hyeongrok Han , Siwon Kim , Hyun-Soo Choi , Sungroh Yoon

While speculative decoding has recently appeared as a promising direction for accelerating the inference of large language models (LLMs), the speedup and scalability are strongly bounded by the token acceptance rate. Prevalent methods…

Machine Learning · Computer Science 2024-10-16 Yunfan Xiong , Ruoyu Zhang , Yanzeng Li , Tianhao Wu , Lei Zou

Speculative decoding has emerged as a widely adopted method to accelerate large language model inference without sacrificing the quality of the model outputs. While this technique has facilitated notable speed improvements by enabling…

Computation and Language · Computer Science 2025-02-12 Jacob K Christopher , Brian R Bartoldson , Tal Ben-Nun , Michael Cardei , Bhavya Kailkhura , Ferdinando Fioretto

Accelerating the inference of large language models (LLMs) has been a critical challenge in generative AI. Speculative decoding (SD) substantially improves LLM inference efficiency. However, its utility is limited by a fundamental…

Computation and Language · Computer Science 2026-05-05 Sibo Xiao , Jinyuan Fu , Zhongle Xie , Lidan Shou

Speculative decoding accelerates large language model (LLM) inference by using a lightweight draft model to propose tokens that are later verified by a stronger target model. While effective in centralized systems, its behavior in…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-11-18 Jingwei Song , Wanyi Chen , Xinyuan Song , Max , Chris Tong , Gufeng Chen , Tianyi Zhao , Eric Yang , Bill Shi , Lynn Ai

Speculative sampling is a popular technique for accelerating inference in Large Language Models by generating candidate tokens using a fast draft model and accepting or rejecting them based on the target model's distribution. While…

Machine Learning · Computer Science 2025-07-08 Valentin De Bortoli , Alexandre Galashov , Arthur Gretton , Arnaud Doucet

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

Speculative decoding is a pivotal technique to accelerate the inference of large language models (LLMs) by employing a smaller draft model to predict the target model's outputs. However, its efficacy can be limited due to the low predictive…

Artificial Intelligence · Computer Science 2024-06-11 Xiaoxuan Liu , Lanxiang Hu , Peter Bailis , Alvin Cheung , Zhijie Deng , Ion Stoica , Hao Zhang

Knowledge distillation (KD) is a technique used to transfer knowledge from an overparameterized teacher network to a less-parameterized student network, thereby minimizing the incurred performance loss. KD methods can be categorized into…

Computer Vision and Pattern Recognition · Computer Science 2024-06-17 Jaeyeon Jang , Young-Ik Kim , Jisu Lim , Hyeonseong Lee

Large-scale contrastive learning models can learn very informative sentence embeddings, but are hard to serve online due to the huge model size. Therefore, they often play the role of "teacher", transferring abilities to small "student"…

Artificial Intelligence · Computer Science 2023-01-31 Chaochen Gao , Xing Wu , Peng Wang , Jue Wang , Liangjun Zang , Zhongyuan Wang , Songlin Hu

Knowledge distillation (KD) is used to enhance automatic speaker verification performance by ensuring consistency between large teacher networks and lightweight student networks at the embedding level or label level. However, the…

Sound · Computer Science 2024-06-28 Duc-Tuan Truong , Ruijie Tao , Jia Qi Yip , Kong Aik Lee , Eng Siong Chng

Speculative decoding (SD) accelerates large language model inference by allowing a lightweight draft model to propose outputs that a stronger target model verifies. However, its token-centric nature allows erroneous steps to propagate.…

Computation and Language · Computer Science 2026-04-17 Kiran Purohit , Ramasuri Narayanam , Soumyabrata Pal