English
Related papers

Related papers: HEAPr: Hessian-based Efficient Atomic Expert Pruni…

200 papers

Mixture-of-Experts (MoE) has demonstrated promising potential in scaling LLMs. However, it is hindered by two critical challenges: (1) substantial GPU memory consumption to load all experts; (2) low activated parameters cannot be…

Machine Learning · Computer Science 2025-08-05 Yuanteng Chen , Yuantian Shao , Peisong Wang , Jian Cheng

Neural network pruning is a practical way for reducing the size of trained models and the number of floating-point operations. One way of pruning is to use the relative Hessian trace to calculate sensitivity of each channel, as compared to…

Computer Vision and Pattern Recognition · Computer Science 2023-06-13 Jack Chong , Manas Gupta , Lihui Chen

Sparse Mixture-of-Experts (SMoE) language models achieve strong capability at low per-token compute, yet deployment remains constrained by memory footprint and throughput because the full expert pool must still be stored and served.…

Machine Learning · Computer Science 2026-04-14 Zongfang Liu , Shengkun Tang , Boyang Sun , Zhiqiang Shen , Xin Yuan

LoRA-MoE has emerged as an effective paradigm for parameter-efficient fine-tuning, combining the low training cost of LoRA with the increased adaptation capacity of Mixture-of-Experts (MoE). However, existing LoRA-MoE frameworks typically…

Machine Learning · Computer Science 2026-04-30 Weihang Li , Jianchun Liu , Hongli Xu

Mixture-of-Experts (MoE) models achieve a favorable trade-off between performance and inference efficiency by activating only a subset of experts. However, the memory overhead of storing all experts remains a major limitation, especially in…

Computation and Language · Computer Science 2025-05-29 Zican Dong , Han Peng , Peiyu Liu , Wayne Xin Zhao , Dong Wu , Feng Xiao , Zhifeng Wang

The sparsely gated mixture of experts (MoE) architecture sends different inputs to different subnetworks, i.e., experts, through trainable routers. MoE reduces the training computation significantly for large models, but its deployment can…

Vision Transformers require significant computational resources and memory bandwidth, severely limiting their deployment on edge devices. While recent structured pruning methods successfully reduce theoretical FLOPs, they typically operate…

Computer Vision and Pattern Recognition · Computer Science 2026-03-13 Andy Li , Aiden Durrant , Milan Markovic , Georgios Leontidis

Mixture-of-Experts (MoE) has emerged as a promising architecture for modern large language models (LLMs). However, massive parameters impose heavy GPU memory (i.e., VRAM) demands, hindering the widespread adoption of MoE LLMs. Offloading…

Machine Learning · Computer Science 2025-09-11 Jiaming Yan , Jianchun Liu , Hongli Xu , Liusheng Huang

Mixture-of-Experts (MoE) large language models (LLMs) are among the top-performing architectures. The largest models, often with hundreds of billions of parameters, pose significant memory challenges for deployment. Traditional approaches…

Artificial Intelligence · Computer Science 2026-04-07 Saurav Jha , Maryam Hashemzadeh , Ali Saheb Pasand , Ali Parviz , Min-Joong Lee , Boris Knyazev

Mixture-of-Experts (MoE) layers have emerged as an important tool in scaling up modern neural networks by decoupling total trainable parameters from activated parameters in the forward pass for each token. However, sparse MoEs add…

Machine Learning · Computer Science 2026-05-22 Tianze Jiang , Blake Bordelon , Cengiz Pehlevan , Boris Hanin

The Mixture-of-Experts (MoE) architecture has demonstrated significant advantages in the era of Large Language Models (LLMs), offering enhanced capabilities with reduced inference costs. However, deploying MoE-based LLMs on…

Machine Learning · Computer Science 2024-11-07 Peng Tang , Jiacheng Liu , Xiaofeng Hou , Yifei Pu , Jing Wang , Pheng-Ann Heng , Chao Li , Minyi Guo

Medical image retrieval (MIR) is a critical component of computer-aided diagnosis, yet existing systems suffer from three persistent limitations: uniform feature encoding that fails to account for the varying clinical importance of…

Computer Vision and Pattern Recognition · Computer Science 2026-03-18 Aojie Yuan

Transformer encoders are widely deployed in large-scale web services for natural language understanding tasks such as text classification, semantic retrieval, and content ranking. However, their high inference latency and memory consumption…

Machine Learning · Computer Science 2025-12-25 Zeli Su , Ziyin Zhang , Wenzheng Zhang , Zhou Liu , Guixian Xu , Wentao Zhang

Mixture of Experts (MoE) has become a mainstream architecture for building Large Language Models (LLMs) by reducing per-token computation while enabling model scaling. It can be viewed as partitioning a large Feed-Forward Network (FFN) at…

Machine Learning · Computer Science 2025-08-27 Weilin Cai , Le Qin , Shwai He , Junwei Cui , Ang Li , Jiayi Huang

A pivotal advancement in the progress of large language models (LLMs) is the emergence of the Mixture-of-Experts (MoE) LLMs. Compared to traditional LLMs, MoE LLMs can achieve higher performance with fewer parameters, but it is still hard…

Computation and Language · Computer Science 2024-05-31 Xudong Lu , Qi Liu , Yuhui Xu , Aojun Zhou , Siyuan Huang , Bo Zhang , Junchi Yan , Hongsheng Li

Neural networks can be drastically shrunk in size by removing redundant parameters. While crucial for the deployment on resource-constraint hardware, oftentimes, compression comes with a severe drop in accuracy and lack of adversarial…

Machine Learning · Computer Science 2024-12-20 Qi Zhao , Christian Wressnegger

The efficient compression of large language models (LLMs) has become increasingly popular. However, recovering the performance of compressed LLMs remains a major challenge. The current practice in LLM compression entails the implementation…

Computation and Language · Computer Science 2024-12-17 Changhai Zhou , Shijie Han , Lining Yang , Yuhua Zhou , Xu Cheng , Yibin Wang , Hongguang Li

Structural pruning can simplify network architecture and improve inference speed. We propose Hardware-Aware Latency Pruning (HALP) that formulates structural pruning as a global resource allocation optimization problem, aiming at maximizing…

Computer Vision and Pattern Recognition · Computer Science 2021-10-22 Maying Shen , Hongxu Yin , Pavlo Molchanov , Lei Mao , Jianna Liu , Jose M. Alvarez

By increasing model parameters but activating them sparsely when performing a task, the use of Mixture-of-Experts (MoE) architecture significantly improves the performance of Large Language Models (LLMs) without increasing the inference…

Computation and Language · Computer Science 2025-06-10 Zeliang Zhang , Xiaodong Liu , Hao Cheng , Chenliang Xu , Jianfeng Gao

Pruning vision-language models (VLMs) for efficient deployment is challenging because compression can affect not only task utility but also visual grounding, often amplifying object hallucinations even at the same sparsity level. We present…

Computer Vision and Pattern Recognition · Computer Science 2026-03-09 Lincen Bai , Hedi Tabia , Raul Santos-Rodriguez