English
Related papers

Related papers: SlimQwen: Exploring the Pruning and Distillation i…

200 papers

Larger transformer models always perform better on various tasks but require more costs to scale up the model size. To efficiently enlarge models, the mixture-of-experts (MoE) architecture is widely adopted, which consists of a gate network…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-11-14 Xiaonan Nie , Qibin Liu , Fangcheng Fu , Shenhan Zhu , Xupeng Miao , Xiaoyang Li , Yang Zhang , Shouda Liu , Bin Cui

Network pruning is one of the most dominant methods for reducing the heavy inference cost of deep neural networks. Existing methods often iteratively prune networks to attain high compression ratio without incurring significant loss in…

Computer Vision and Pattern Recognition · Computer Science 2020-08-17 Duong H. Le , Trung-Nhan Vo , Nam Thoai

Pre-trained language models achieve superior performance but are computationally expensive. Techniques such as pruning and knowledge distillation have been developed to reduce their sizes and latencies. In this work, we propose a structured…

Computation and Language · Computer Science 2023-05-19 Ziqing Yang , Yiming Cui , Xin Yao , Shijin Wang

The Mixture-of-Experts (MoE) technique has proven to be a promising solution to efficiently scale the model size, which has been widely applied in recent LLM advancements. However, the substantial memory overhead of MoE models has made…

Machine Learning · Computer Science 2025-10-17 Ruijie Miao , Yilun Yao , Zihan Wang , Zhiming Wang , Bairen Yi , LingJun Liu , Yikai Zhao , Tong Yang

Deep pre-trained Transformer models have achieved state-of-the-art results over a variety of natural language processing (NLP) tasks. By learning rich language knowledge with millions of parameters, these models are usually…

Computation and Language · Computer Science 2020-11-10 Zhengyan Zhang , Fanchao Qi , Zhiyuan Liu , Qun Liu , Maosong Sun

With the rapid development of deep learning, large language models have shown strong capabilities in complex reasoning tasks such as mathematical equation solving. However, their substantial computational and storage costs hinder practical…

Machine Learning · Computer Science 2025-11-25 Fengming Yu , Qingyu Meng , Haiwei Pan , Kejia Zhang

Knowledge distillation (KD) is the de facto standard for compressing large-scale models into smaller ones. Prior works have explored ever more complex KD strategies involving different objective functions, teacher-ensembles, and weight…

Computer Vision and Pattern Recognition · Computer Science 2025-05-06 Vishaal Udandarao , Nikhil Parthasarathy , Muhammad Ferjad Naeem , Talfan Evans , Samuel Albanie , Federico Tombari , Yongqin Xian , Alessio Tonioni , Olivier J. Hénaff

Knowledge Distillation (KD) is a model compression algorithm that helps transfer the knowledge of a large neural network into a smaller one. Even though KD has shown promise on a wide range of Natural Language Processing (NLP) applications,…

Computation and Language · Computer Science 2021-09-21 Tianda Li , Ahmad Rashid , Aref Jafari , Pranav Sharma , Ali Ghodsi , Mehdi Rezagholizadeh

Mixture-of-experts (MoE) is gaining increasing attention due to its unique properties and remarkable performance, especially for language tasks. By sparsely activating a subset of parameters for each token, MoE architecture could increase…

Computation and Language · Computer Science 2025-06-24 Ka Man Lo , Zeyu Huang , Zihan Qiu , Zili Wang , Jie Fu

Structured pruning has been extensively studied on monolingual pre-trained language models and is yet to be fully evaluated on their multilingual counterparts. This work investigates three aspects of structured pruning on multilingual…

Computation and Language · Computer Science 2022-04-07 Yanyang Li , Fuli Luo , Runxin Xu , Songfang Huang , Fei Huang , Liwei Wang

Structured pruning is a widely used technique for reducing the size of pre-trained language models (PLMs), but current methods often overlook the potential of compressing the hidden dimension (d) in PLMs, a dimension critical to model size…

Computation and Language · Computer Science 2024-08-20 Yuxuan Hu , Jing Zhang , Zhe Zhao , Chen Zhao , Xiaodong Chen , Cuiping Li , Hong Chen

Mixture-of-Experts (MoE) architectures in large language models (LLMs) achieve exceptional performance, but face prohibitive storage and memory requirements. To address these challenges, we present $D^2$-MoE, a new delta decompression…

Machine Learning · Computer Science 2025-02-25 Hao Gu , Wei Li , Lujun Li , Qiyuan Zhu , Mark Lee , Shengjie Sun , Wei Xue , Yike Guo

This study presents an ensemble technique, SPQ (SVD-Pruning-Quantization), for large language model (LLM) compression that combines variance-retained singular value decomposition (SVD), activation-based pruning, and post-training linear…

Computation and Language · Computer Science 2026-02-23 Jiamin Yao , Eren Gultepe

Large language models have driven significant progress in natural language processing, but their deployment requires substantial compute and memory resources. As models scale, compression techniques become essential for balancing model…

Machine Learning · Computer Science 2025-05-13 Vithursan Thangarasa , Ganesh Venkatesh , Mike Lasby , Nish Sinnadurai , Sean Lie

With the increasing size of datasets used for training neural networks, data pruning becomes an attractive field of research. However, most current data pruning algorithms are limited in their ability to preserve accuracy compared to models…

Computer Vision and Pattern Recognition · Computer Science 2024-08-15 Emanuel Ben-Baruch , Adam Botach , Igor Kviatkovsky , Manoj Aggarwal , Gérard Medioni

Recent Mixture-of-Experts (MoE)-based large language models (LLMs) such as Qwen-MoE and DeepSeek-MoE are transforming generative AI in natural language processing. However, these models require vast and diverse training data. Federated…

Machine Learning · Computer Science 2026-02-17 Songyuan Li , Jia Hu , Ahmed M. Abdelmoniem , Geyong Min , Haojun Huang , Jiwei Huang

Hybrid LLM architectures that combine Attention and State Space Models (SSMs) achieve state-of-the-art accuracy and runtime performance. Recent work has demonstrated that applying compression and distillation to Attention-only models yields…

Compressing and pruning large machine learning models has become a critical step towards their deployment in real-world applications. Standard pruning and compression techniques are typically designed without taking the structure of the…

The pruning objective has recently extended beyond accuracy and sparsity to robustness in language models. Despite this, existing methods struggle to enhance robustness against adversarial attacks when continually increasing model sparsity…

Computation and Language · Computer Science 2024-01-12 Jianwei Li , Qi Lei , Wei Cheng , Dongkuan Xu

With numerous medical tasks, the performance of deep models has recently experienced considerable improvements. These models are often adept learners. Yet, their intricate architectural design and high computational complexity make…

Image and Video Processing · Electrical Eng. & Systems 2023-03-17 Eddardaa Ben Loussaief , Hatem Rashwan , Mohammed Ayad , Mohammed Zakaria Hassan , Domenec Puig
‹ Prev 1 3 4 5 6 7 10 Next ›