English
Related papers

Related papers: Lifting the Curse of Capacity Gap in Distilling La…

200 papers

Language model (LM) distillation aims at distilling the knowledge in a large teacher LM to a small student one. As a critical issue facing LM distillation, a superior student often arises from a teacher of a relatively small scale instead…

Computation and Language · Computer Science 2025-07-31 Chen Zhang , Qiuchi Li , Dawei Song , Zheyu Ye , Yan Gao , Yan Hu

Mixture-of-Experts (MoE) based Large Language Models (LLMs) have demonstrated impressive performance and computational efficiency. However, their deployment is often constrained by substantial memory demands, primarily due to the need to…

Machine Learning · Computer Science 2026-03-16 Jiawei Hao , Zhiwei Hao , Jianyuan Guo , Li Shen , Yong Luo , Han Hu , Dan Zeng

Knowledge distillation aims at obtaining a compact and effective model by learning the mapping function from a much larger one. Due to the limited capacity of the student, the student would underfit the teacher. Therefore, student…

Machine Learning · Computer Science 2021-01-13 Jia Guo , Minghao Chen , Yao Hu , Chen Zhu , Xiaofei He , Deng Cai

The Mixture of Experts (MoE) is an effective architecture for scaling large language models by leveraging sparse expert activation to balance performance and efficiency. However, under expert parallelism, MoE suffers from inference…

Machine Learning · Computer Science 2026-05-12 Shwai He , Weilin Cai , Jiayi Huang , Ang Li

Knowledge distillation from large language models (LLMs) assumes that the teacher's output distribution is a high-quality training signal. On reasoning tasks, this assumption is frequently violated. A model's intermediate representations…

Computation and Language · Computer Science 2026-03-16 Ryan Brown , Chris Russell

Large-scale language models have recently demonstrated impressive empirical performance. Nevertheless, the improved results are attained at the price of bigger models, more power consumption, and slower inference, which hinder their…

Computation and Language · Computer Science 2021-03-18 Kevin J Liang , Weituo Hao , Dinghan Shen , Yufan Zhou , Weizhu Chen , Changyou Chen , Lawrence Carin

Mixture of experts (MoE) is a popular technique to improve capacity of Large Language Models (LLMs) with conditionally-activated parallel experts. However, serving MoE models on memory-constrained devices is challenging due to the large…

Artificial Intelligence · Computer Science 2024-05-30 Rui Kong , Yuanchun Li , Qingtian Feng , Weijun Wang , Xiaozhou Ye , Ye Ouyang , Linghe Kong , Yunxin Liu

Large language models (LLMs) excel in complex reasoning tasks, and distilling their reasoning capabilities into smaller models has shown promise. However, we uncover an interesting phenomenon, which we term the Small Model Learnability Gap:…

Artificial Intelligence · Computer Science 2025-11-14 Yuetai Li , Xiang Yue , Zhangchen Xu , Fengqing Jiang , Luyao Niu , Bill Yuchen Lin , Bhaskar Ramasubramanian , Radha Poovendran

The Mixture of Experts (MoE) architecture has emerged as a powerful paradigm for scaling large language models (LLMs) while maintaining inference efficiency. However, their enormous memory requirements make them prohibitively expensive to…

Machine Learning · Computer Science 2025-06-24 Zichong Li , Chen Liang , Zixuan Zhang , Ilgee Hong , Young Jin Kim , Weizhu Chen , Tuo Zhao

Transferring the reasoning capability from stronger large language models (LLMs) to smaller ones has been quite appealing, as smaller LLMs are more flexible to deploy with less expense. Among the existing solutions, knowledge distillation…

Computation and Language · Computer Science 2024-11-26 Yijun Tian , Yikun Han , Xiusi Chen , Wei Wang , Nitesh V. Chawla

Large Language Models (LLMs) have achieved impressive results across various tasks, yet their high computational demands pose deployment challenges, especially on consumer-grade hardware. Mixture of Experts (MoE) models provide an efficient…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-12-19 En-Ming Huang , Li-Shang Lin , Chun-Yi Lee

Sparse Mixture-of-Experts (MoE) has been a successful approach for scaling multilingual translation models to billions of parameters without a proportional increase in training computation. However, MoE models are prohibitively large and…

Computation and Language · Computer Science 2021-10-11 Sneha Kudugunta , Yanping Huang , Ankur Bapna , Maxim Krikun , Dmitry Lepikhin , Minh-Thang Luong , Orhan Firat

Knowledge distillation allows smaller neural networks to emulate the performance of larger, teacher models with reduced computational demands. Traditional methods for Large Language Models (LLMs) often necessitate extensive fine-tuning,…

Computation and Language · Computer Science 2025-05-02 Tyler McDonald , Ali Emami

The crux of knowledge distillation is to effectively train a resource-limited student model with the guide of a pre-trained larger teacher model. However, when there is a large difference between the model complexities of teacher and…

Machine Learning · Computer Science 2021-06-01 Aryan Asadian , Amirali Salehi-Abari

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

Recent studies have uncovered that language model distillation is less effective when facing a large capacity gap between the teacher and the student, and introduced teacher assistant-based distillation to bridge the gap. As a connection,…

Computation and Language · Computer Science 2024-01-30 Chen Zhang , Yang Yang , Qifan Wang , Jiahao Liu , Jingang Wang , Wei Wu , Dawei Song

Mixture-of-Experts (MoE) models have shown strong potential in scaling language models efficiently by activating only a small subset of experts per input. However, their widespread deployment remains limited due to the high memory overhead…

Machine Learning · Computer Science 2025-11-10 Yushu Zhao , Zheng Wang , Minjia Zhang

Scaling up the number of parameters of language models has proven to be an effective approach to improve performance. For dense models, increasing model size proportionally increases the model's computation footprint. In this work, we seek…

Computation and Language · Computer Science 2023-11-21 Cicero Nogueira dos Santos , James Lee-Thorp , Isaac Noble , Chung-Ching Chang , David Uthus

Knowledge distillation typically involves transferring knowledge from a Large Language Model (LLM) to a Smaller Language Model (SLM). However, in tasks such as text matching, fine-tuned smaller models often yield more effective…

Computation and Language · Computer Science 2025-07-09 Mingzhe Li , Jing Xiang , Qishen Zhang , Kaiyang Wan , Xiuying Chen

Knowledge distillation is typically conducted by training a small model (the student) to mimic a large and cumbersome model (the teacher). The idea is to compress the knowledge from the teacher by using its output probabilities as…

Computation and Language · Computer Science 2020-01-17 Gustavo Aguilar , Yuan Ling , Yu Zhang , Benjamin Yao , Xing Fan , Chenlei Guo
‹ Prev 1 2 3 10 Next ›