中文
相关论文

相关论文: MoNE: Replacing Redundant Experts with Lightweight…

200 篇论文

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…

Mixture-of-Experts (MoE) has garnered significant attention for its ability to scale up neural networks while utilizing the same or even fewer active parameters. However, MoE does not alleviate the massive memory requirements of networks,…

机器学习 · 计算机科学 2026-04-21 Mingyu Cao , Gen Li , Jie Ji , Jiaqi Zhang , Ajay Jaiswal , Li Shen , Xiaolong Ma , Shiwei Liu , Lu Yin

Scaling large language models has driven remarkable advancements across various domains, yet the continual increase in model size presents significant challenges for real-world deployment. The Mixture of Experts (MoE) architecture offers a…

机器学习 · 计算机科学 2025-03-18 Shwai He , Daize Dong , Liang Ding , Ang Li

The visual medium (images and videos) naturally contains a large amount of information redundancy, thereby providing a great opportunity for leveraging efficiency in processing. While Vision Transformer (ViT) based models scale effectively…

计算机视觉与模式识别 · 计算机科学 2024-07-31 Gagan Jain , Nidhi Hegde , Aditya Kusupati , Arsha Nagrani , Shyamal Buch , Prateek Jain , Anurag Arnab , Sujoy Paul

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…

计算与语言 · 计算机科学 2025-06-10 Zeliang Zhang , Xiaodong Liu , Hao Cheng , Chenliang Xu , Jianfeng Gao

Mixture-of-Experts (MoE) architectures face challenges such as high memory consumption and redundancy in experts. Pruning MoE can reduce network weights while maintaining model performance. Motivated by the recent observation of emergent…

计算与语言 · 计算机科学 2024-10-17 Yanyue Xie , Zhi Zhang , Ding Zhou , Cong Xie , Ziang Song , Xin Liu , Yanzhi Wang , Xue Lin , An Xu

Mixture-of-Experts (MoE) models have become a key approach for scaling large language models efficiently by activating only a subset of experts during training and inference. Typically, the number of activated experts presents a trade-off:…

机器学习 · 计算机科学 2025-09-04 Yifei He , Yang Liu , Chen Liang , Hany Hassan Awadalla

Mixture-of-Experts (MoE) is now the dominant architecture for frontier language models, yet it requires all expert parameters to be loaded in memory, making it less preferable for memory-constrained deployment. Existing compression methods…

计算与语言 · 计算机科学 2026-05-28 Junhyuck Kim , Jihun Yun , Haechan Kim , Gyeongman Kim , Joonghyun Bae , Jaewoong Cho

In this work, we first explore whether the parameters activated by the MoE layer remain highly sparse at inference. We perform a sparsification study on several representative MoE models. For each expert, we rank parameters by the magnitude…

计算与语言 · 计算机科学 2025-10-08 Runxi Cheng , Yuchen Guan , Yucheng Ding , Qingguo Hu , Yongxian Wei , Chun Yuan , Yelong Shen , Weizhu Chen , Yeyun Gong

The sparse Mixture-of-Experts (MoE) model is powerful for large-scale pre-training and has achieved promising results due to its model capacity. However, with trillions of parameters, MoE is hard to be deployed on cloud or mobile…

机器学习 · 计算机科学 2022-06-03 Tianyu Chen , Shaohan Huang , Yuan Xie , Binxing Jiao , Daxin Jiang , Haoyi Zhou , Jianxin Li , Furu Wei

The Mixture of Experts (MoE) is a widely known neural architecture where an ensemble of specialized sub-models optimizes overall performance with a constant computational cost. However, conventional MoEs pose challenges at scale due to the…

计算与语言 · 计算机科学 2023-09-12 Ted Zadouri , Ahmet Üstün , Arash Ahmadian , Beyza Ermiş , Acyr Locatelli , Sara Hooker

Despite the significant breakthrough of Mixture-of-Experts (MoE), the increasing scale of these MoE models presents huge memory and storage challenges. Existing MoE pruning methods, which involve reducing parameter size with a uniform…

计算与语言 · 计算机科学 2025-09-22 Sikai Bai , Haoxi Li , Jie Zhang , Zicong Hong , Song Guo

The emergence of Mixture of Experts (MoE) LLMs has significantly advanced the development of language models. Compared to traditional LLMs, MoE LLMs outperform traditional LLMs by achieving higher performance with considerably fewer…

机器学习 · 计算机科学 2024-11-05 Cheng Yang , Yang Sui , Jinqi Xiao , Lingyi Huang , Yu Gong , Yuanlin Duan , Wenqi Jia , Miao Yin , Yu Cheng , Bo Yuan

Mixture-of-Experts (MoE) activates only a subset of experts during inference, allowing the model to maintain low inference FLOPs and latency even as the parameter count scales up. However, since MoE dynamically selects the experts, all the…

机器学习 · 计算机科学 2025-05-27 Shibo Jie , Yehui Tang , Kai Han , Yitong Li , Duyu Tang , Zhi-Hong Deng , Yunhe Wang

The Mixture of Experts (MoE) selects a few feed-forward networks (FFNs) per token, achieving an effective trade-off between computational cost and performance. In conventional MoE, each expert is treated as entirely independent, and experts…

机器学习 · 计算机科学 2026-01-27 Shota Takashiro , Takeshi Kojima , Shohei Taniguchi , Yusuke Iwasawa , Yutaka Matsuo

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…

机器学习 · 计算机科学 2026-03-16 Jiawei Hao , Zhiwei Hao , Jianyuan Guo , Li Shen , Yong Luo , Han Hu , Dan Zeng

Mixture-of-Experts (MoE) large language models (LLM) have memory requirements that often exceed the GPU memory capacity, requiring costly parameter movement from secondary memories to the GPU for expert computation. In this work, we present…

机器学习 · 计算机科学 2024-05-30 Taehyun Kim , Kwanseok Choi , Youngmock Cho , Jaehoon Cho , Hyuk-Jae Lee , Jaewoong Sim

Mixture-of-Experts (MoE) models scale large language models efficiently by sparsely activating experts, but once an expert is selected, it is executed fully. Hence, the trade-off between accuracy and computation in an MoE model typically…

机器学习 · 计算机科学 2026-02-09 Nurbek Tastan , Stefanos Laskaridis , Karthik Nandakumar , Samuel Horvath

Mixture-of-Experts (MoE) architectures have emerged as a promising paradigm for scaling large language models (LLMs) with sparse activation of task-specific experts. Despite their computational efficiency during inference, the massive…

计算与语言 · 计算机科学 2025-04-11 Hongcheng Guo , Juntao Yao , Boyang Wang , Junjia Du , Shaosheng Cao , Donglin Di , Shun Zhang , Zhoujun Li

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…

计算与语言 · 计算机科学 2025-05-29 Zican Dong , Han Peng , Peiyu Liu , Wayne Xin Zhao , Dong Wu , Feng Xiao , Zhifeng Wang
‹ 上一页 1 2 3 10 下一页 ›