English
Related papers

Related papers: DistillSpec: Improving Speculative Decoding via Kn…

200 papers

Large Language Models (LLMs) have become more prevalent in long-context applications such as interactive chatbots, document analysis, and agent workflows, but it is challenging to serve long-context requests with low latency and high…

Computation and Language · Computer Science 2025-04-03 Ranajoy Sadhukhan , Jian Chen , Zhuoming Chen , Vashisth Tiwari , Ruihang Lai , Jinyuan Shi , Ian En-Hsu Yen , Avner May , Tianqi Chen , Beidi Chen

Speculative decoding (SD) has emerged as a promising approach to accelerate LLM inference without sacrificing output quality. Existing SD methods tailored for video-LLMs primarily focus on pruning redundant visual tokens to mitigate the…

Computer Vision and Pattern Recognition · Computer Science 2026-01-14 Qitan Lv , Tianyu Liu , Wen Wu , Xuenan Xu , Bowen Zhou , Feng Wu , Chao Zhang

In this paper, we propose Stochastic Knowledge Distillation (SKD) to obtain compact BERT-style language model dubbed SKDBERT. In each iteration, SKD samples a teacher model from a pre-defined teacher ensemble, which consists of multiple…

Computation and Language · Computer Science 2022-11-30 Zixiang Ding , Guoqing Jiang , Shuai Zhang , Lin Guo , Wei Lin

Speculative decoding significantly accelerates language model inference by enabling a lightweight draft model to propose multiple tokens that a larger target model verifies simultaneously. However, applying this technique to vision-language…

Machine Learning · Computer Science 2025-05-20 Mugilan Ganesan , Shane Segal , Ankur Aggarwal , Nish Sinnadurai , Sean Lie , Vithursan Thangarasa

Knowledge Distillation (KD) compresses computationally expensive pre-trained language models (PLMs) by transferring their knowledge to smaller models, allowing their use in resource-constrained or real-time settings. However, most smaller…

Computation and Language · Computer Science 2023-11-08 Hayeon Lee , Rui Hou , Jongpil Kim , Davis Liang , Hongbo Zhang , Sung Ju Hwang , Alexander Min

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

Vision-language models (VLMs) have demonstrated strong capabilities in multimodal perception and reasoning. However, deploying large VLMs on mobile devices remains challenging due to their substantial computational and memory demands. A…

Artificial Intelligence · Computer Science 2026-05-05 Yuanyuan Jia , Shunpu Tang , Qianqian Yang

Speculative decoding accelerates memory-bound LLM inference without quality degradation by using a fast drafter to propose multiple candidate tokens and the target model to verify them in parallel. However, conventional sequential…

Computation and Language · Computer Science 2026-05-20 Yaojie Zhang , Jianuo Huang , Junlong Ke , Yuhang Han , Yongji Long , Tianchen Zhao , Biqing Qi , Linfeng Zhang

Self-supervised learning solves pretext prediction tasks that do not require annotations to learn feature representations. For vision tasks, pretext tasks such as predicting rotation, solving jigsaw are solely created from the input data.…

Computer Vision and Pattern Recognition · Computer Science 2021-07-01 Prashant Bhat , Elahe Arani , Bahram Zonooz

Autoregressive sampling from large language models has led to state-of-the-art results in several natural language tasks. However, autoregressive sampling generates tokens one at a time making it slow, and even prohibitive in certain tasks.…

Machine Learning · Computer Science 2024-01-19 Ziteng Sun , Ananda Theertha Suresh , Jae Hun Ro , Ahmad Beirami , Himanshu Jain , Felix Yu

Large language models (LLMs) have achieved remarkable performance across a wide range of tasks, but their increasing parameter sizes significantly slow down inference. Speculative decoding mitigates this issue by leveraging a smaller draft…

Computation and Language · Computer Science 2026-05-27 Kuan-Wei Lu , Ding-Yong Hong , Pangfeng Liu , Jan-Jan Wu

Knowledge Distillation (KD) aims to transfer knowledge from a large teacher model to a smaller student model. While contrastive learning has shown promise in self-supervised learning by creating discriminative representations, its…

Computer Vision and Pattern Recognition · Computer Science 2025-05-14 Nikolaos Giakoumoglou , Tania Stathaki

Speculative decoding accelerates autoregressive generation by letting a lightweight draft model propose future tokens that a larger target model then verifies in parallel. In practice, however, draft models are usually trained on broad…

Computation and Language · Computer Science 2026-03-31 Mohamad Zbib , Mohamad Bazzi , Ammar Mohanna , Hasan Abed Al Kader Hammoud , Bernard Ghanem

Existing techniques for accelerating language model inference, such as speculative decoding, require training auxiliary speculator models and building and deploying complex inference pipelines. We consider a new approach for converting a…

Computation and Language · Computer Science 2026-04-27 John Kirchenbauer , Abhimanyu Hans , Brian Bartoldson , Micah Goldblum , Ashwinee Panda , Tom Goldstein

We propose the task of knowledge distillation detection, which aims to determine whether a student model has been distilled from a given teacher, under a practical setting where only the student's weights and the teacher's API are…

Machine Learning · Computer Science 2025-10-03 Qin Shi , Amber Yijia Zheng , Qifan Song , Raymond A. Yeh

Speculative decoding accelerates large language model (LLM) inference by using a small draft model to generate candidate tokens for a larger target model to verify. The efficacy of this technique hinges on the trade-off between the time…

Computation and Language · Computer Science 2026-03-03 Jiebin Zhang , Zhenghan Yu , Liang Wang , Nan Yang , Eugene J. Yu , Zheng Li , Yifan Song , Dawei Zhu , Xingxing Zhang , Furu Wei , Sujian Li

Previous Knowledge Distillation based efficient image retrieval methods employs a lightweight network as the student model for fast inference. However, the lightweight student model lacks adequate representation capacity for effective…

Computer Vision and Pattern Recognition · Computer Science 2023-10-06 Yi Xie , Huaidong Zhang , Xuemiao Xu , Jianqing Zhu , Shengfeng He

This paper explores the use of knowledge distillation to improve a Multi-Task Deep Neural Network (MT-DNN) (Liu et al., 2019) for learning text representations across multiple natural language understanding tasks. Although ensemble learning…

Computation and Language · Computer Science 2019-04-23 Xiaodong Liu , Pengcheng He , Weizhu Chen , Jianfeng Gao

Spiking neural networks (SNNs), which are brain-inspired and spike-driven, achieve high energy efficiency. However, a performance gap between SNNs and artificial neural networks (ANNs) still remains. Knowledge distillation (KD) is commonly…

Machine Learning · Computer Science 2026-05-15 Kai Sun , Peibo Duan , Yongsheng Huang , Guowei Zhang , Benjamin Smith , Nanxu Gong , Levin Kuhlmann

Speculative decoding is a powerful technique that attempts to circumvent the autoregressive constraint of modern Large Language Models (LLMs). The aim of speculative decoding techniques is to improve the average inference time of a large,…

Computation and Language · Computer Science 2024-10-25 Sudhanshu Agrawal , Wonseok Jeon , Mingu Lee