English
Related papers

Related papers: EMO: Frustratingly Easy Progressive Training of Ex…

200 papers

Mixture-of-Experts (MoE) architectures enable efficient scaling of large language models by activating only a subset of parameters per input. However, existing MoE models suffer from two critical limitations: (1) inefficient token-to-expert…

Computation and Language · Computer Science 2025-10-10 Jing Li , Zhijie Sun , Dachao Lin , Xuan He , Binfan Zheng , Yi Lin , Rongqian Zhao , Xin Chen

The Mixture-of-Experts (MoE) model has emerged as a prominent architecture in the field of Large Language Models (LLMs), providing a better balance between model performance and computational efficiency. However the General Matrix Multiply…

Computation and Language · Computer Science 2025-01-06 Yulei Qian , Fengcun Li , Xiangyang Ji , Xiaoyu Zhao , Jianchao Tan , Kefeng Zhang , Xunliang Cai

Mixture-of-Experts (MoE) models are crucial for scaling model capacity while controlling inference costs. While integrating MoE into multimodal models like CLIP improves performance, training these models is notoriously challenging and…

Computer Vision and Pattern Recognition · Computer Science 2025-05-27 Xinze Wang , Chen Chen , Yinfei Yang , Hong-You Chen , Bowen Zhang , Aditya Pal , Xiangxin Zhu , Xianzhi Du

Mixture of Experts (MoEs) have become a central component of many state-of-the-art open-source and proprietary large language models. Despite their widespread adoption, it remains unclear how close existing MoE architectures are to optimal…

Mixture of Experts (MoE) are rising in popularity as a means to train extremely large-scale models, yet allowing for a reasonable computational cost at inference time. Recent state-of-the-art approaches usually assume a large number of…

Computer Vision and Pattern Recognition · Computer Science 2023-04-13 Amelie Royer , Ilia Karmanov , Andrii Skliar , Babak Ehteshami Bejnordi , Tijmen Blankevoort

Mixture-of-Experts (MoE) models facilitate edge deployment by decoupling model capacity from active computation, yet their large memory footprint drives the need for GPU systems with near-data processing (NDP) capabilities that offload…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-01-08 Qi Wu , Chao Fang , Jiayuan Chen , Ye Lin , Yueqi Zhang , Yichuan Bai , Yuan Du , Li Du

Mixture of Experts (MoE) pretraining is more scalable than dense Transformer pretraining, because MoEs learn to route inputs to a sparse set of their feedforward parameters. However, this means that MoEs only receive a sparse backward…

Machine Learning · Computer Science 2025-11-05 Ashwinee Panda , Vatsal Baherwani , Zain Sarwar , Benjamin Therien , Sambit Sahu , Tom Goldstein , Supriyo Chakraborty

Mixture of Experts (MoE) models have become central to scaling large language models, yet their mechanistic differences from dense networks remain poorly understood. Previous work has explored how dense models use \textit{superposition} to…

Machine Learning · Computer Science 2025-12-29 Marmik Chaudhari , Jeremi Nuer , Rome Thorstenson

Larger networks generally have greater representational power at the cost of increased computational complexity. Sparsifying such networks has been an active area of research but has been generally limited to static regularization or…

Computer Vision and Pattern Recognition · Computer Science 2019-04-15 Xin Wang , Fisher Yu , Lisa Dunlap , Yi-An Ma , Ruth Wang , Azalia Mirhoseini , Trevor Darrell , Joseph E. Gonzalez

Sparse Mixture-of-Experts (SMoE) architectures have enabled a new frontier in scaling Large Language Models (LLMs), offering superior performance by activating only a fraction of their total parameters during inference. However, their…

Machine Learning · Computer Science 2025-11-26 Wentao Hu , Mingkuan Zhao , Shuangyong Song , Xiaoyan Zhu , Xin Lai , Jiayin Wang

Large multimodal Mixture-of-Experts (MoEs) effectively scale the model size to boost performance while maintaining fixed active parameters. However, previous works primarily utilized full-precision experts during sparse up-cycling. Despite…

Computer Vision and Pattern Recognition · Computer Science 2026-01-08 Hongyu Wang , Jiayu Xu , Ruiping Wang , Yan Feng , Yitao Zhai , Peng Pei , Xunliang Cai , Xilin Chen

Mixture-of-Experts (MoE) has emerged as a promising paradigm for foundation models due to its efficient and powerful scalability. In this work, we present Sigma-MoE-Tiny, an MoE language model that achieves the highest sparsity compared to…

The Mixture-of-Experts (MoE) technique can scale up the model size of Transformers with an affordable computational overhead. We point out that existing learning-to-route MoE methods suffer from the routing fluctuation issue, i.e., the…

Machine Learning · Computer Science 2022-04-19 Damai Dai , Li Dong , Shuming Ma , Bo Zheng , Zhifang Sui , Baobao Chang , Furu Wei

Scaling laws for Large Language Models govern macroscopic resource allocation, yet translating them into precise Mixture-of-Experts (MoE) architectural configurations remains an open problem due to the combinatorially vast design space.…

Machine Learning · Computer Science 2026-03-24 Weilin Wan , Jingtao Han , Weizhong Zhang , Cheng Jin

Mixture-of-Experts (MoE) has emerged as an effective approach to reduce the computational overhead of Transformer architectures by sparsely activating a subset of parameters for each token while preserving high model capacity. This paradigm…

Computer Vision and Pattern Recognition · Computer Science 2026-03-31 Dohwan Ko , Jinyoung Park , Seoung Choi , Sanghyeok Lee , Seohyun Lee , Hyunwoo J. Kim

Sparse Mixture of Expert (MoE) models are popular foundational architectures at large scale, however, under-explored at smaller sizes. Here, we show how to enable Compact Sparse Mixture of Experts (CoSMoEs) for on-device inference.…

Machine Learning · Computer Science 2025-03-04 Patrick Huber , Akshat Shrivastava , Ernie Chang , Chinnadhurai Sankar , Ahmed Aly , Adithya Sagar

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…

While transformers and their variant conformers show promising performance in speech recognition, the parameterized property leads to much memory cost during training and inference. Some works use cross-layer weight-sharing to reduce the…

Audio and Speech Processing · Electrical Eng. & Systems 2022-09-20 Ye Bai , Jie Li , Wenjing Han , Hao Ni , Kaituo Xu , Zhuo Zhang , Cheng Yi , Xiaorui Wang

Sparsely-activated Mixture-of-experts (MoE) models allow the number of parameters to greatly increase while keeping the amount of computation for a given token or a given sample unchanged. However, a poor expert routing strategy (e.g. one…

Machine Learning · Computer Science 2022-10-17 Yanqi Zhou , Tao Lei , Hanxiao Liu , Nan Du , Yanping Huang , Vincent Zhao , Andrew Dai , Zhifeng Chen , Quoc Le , James Laudon

Recently, inspired by the concept of sparsity, Mixture-of-Experts (MoE) models have gained increasing popularity for scaling model size while keeping the number of activated parameters constant. In this study, we thoroughly investigate the…

Computation and Language · Computer Science 2024-11-26 Xiaoye Qu , Daize Dong , Xuyang Hu , Tong Zhu , Weigao Sun , Yu Cheng