English
Related papers

Related papers: Exploiting Activation Sparsity with Dense to Dynam…

200 papers

Mixture of Experts (MoE) achieve parameter-efficient scaling through sparse expert routing, yet their internal representations remain poorly understood compared to dense models. We present a systematic comparison of MoE and dense model…

Machine Learning · Computer Science 2026-03-09 Marmik Chaudhari , Nishkal Hundia , Idhant Gulati

Efficient inference is a critical challenge in deep generative modeling, particularly as diffusion models grow in capacity and complexity. While increased complexity often improves accuracy, it raises compute costs, latency, and memory…

Machine Learning · Computer Science 2025-09-24 Siu Hang Ho , Prasad Ganesan , Nguyen Duong , Daniel Schlabig

Mixture-of-Experts (MoE) architectures have become the dominant choice for scaling Large Language Models (LLMs), activating only a subset of parameters per token. While MoE architectures are primarily adopted for computational efficiency,…

Computation and Language · Computer Science 2026-05-19 Jeremy Herbst , Stefan Wermter , Jae Hee Lee

Mixture-of-Experts (MoE) architectures enhance the efficiency of large language models by activating only a subset of experts per token. However, standard MoE employs a fixed Top-K routing strategy, leading to redundant computation and…

Artificial Intelligence · Computer Science 2026-05-15 Juntong Wu , Jialiang Cheng , Qishen Yin , Yue Dai , Yuliang Yan , Fuyu Lv , Ou Dan , Li Yuan

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

The Mixture-of-Experts (MoE) architecture is showing promising results in improving parameter sharing in multi-task learning (MTL) and in scaling high-capacity neural networks. State-of-the-art MoE models use a trainable sparse gate to…

Mixture-of-Experts (MoE) architectures leverage sparse activation to enhance the scalability of large language models (LLMs), making them suitable for deployment in resource-constrained edge networks. However, the sheer number of experts…

Information Theory · Computer Science 2026-03-26 Qian Chen , Xianhao Chen , Kaibin Huang

Mixture-of-Experts (MoE) enjoys performance gain by increasing model capacity while keeping computation cost constant. When comparing MoE to dense models, prior work typically adopt the following setting: 1) use FLOPs or activated…

Machine Learning · Computer Science 2024-07-02 Xianzhi Du , Tom Gunter , Xiang Kong , Mark Lee , Zirui Wang , Aonan Zhang , Nan Du , Ruoming Pang

Sparse Mixtures of Experts (MoEs) are typically trained to operate at a fixed sparsity level, e.g. $k$ in a top-$k$ gating function. This global sparsity level determines an operating point on the accuracy/latency curve; currently, meeting…

Scaling the size of language models usually leads to remarkable advancements in NLP tasks. But it often comes with a price of growing computational cost. Although a sparse Mixture of Experts (MoE) can reduce the cost by activating a small…

Computation and Language · Computer Science 2023-11-23 Shwai He , Run-Ze Fan , Liang Ding , Li Shen , Tianyi Zhou , Dacheng Tao

Mixture-of-Experts layers achieve compute efficiency through weight sparsity: each token activates only a subset of experts. Data sparsity, where each expert processes only a subset of tokens, offers a complementary axis. Expert-choice…

Machine Learning · Computer Science 2026-01-23 Maciej Kilian , Oleg Mkrtchyan , Luke Zettlemoyer , Akshat Shrivastava , Armen Aghajanyan

Sparse Mixture of Experts (MoE) models offer a scalable and efficient architecture for training large neural networks by activating only a subset of parameters ("experts") for each input. A learned router computes a distribution over these…

Machine Learning · Computer Science 2025-10-14 Nabil Omi , Siddhartha Sen , Ali Farhadi

We study dense and mixture-of-experts (MoE) transformers in a tiny-scale pretraining regime under a shared LLaMA-style decoder training recipe. The sparse model replaces dense feed-forward blocks with Mixtral-style routed experts. Dense…

Computation and Language · Computer Science 2026-05-14 Abdalrahman Wael

Sparse Mixture-of-Experts (MoE) architectures effectively scale model capacity by activating only a subset of experts for each input token. However, the standard Top-k routing strategy imposes a uniform sparsity pattern that ignores the…

Artificial Intelligence · Computer Science 2025-12-17 Can Jin , Hongwu Peng , Mingcan Xiang , Qixin Zhang , Xiangchi Yuan , Amit Hasan , Ohiremen Dibua , Yifan Gong , Yan Kang , Dimitris N. Metaxas

Scale has opened new frontiers in natural language processing -- but at a high cost. In response, Mixture-of-Experts (MoE) and Switch Transformers have been proposed as an energy efficient path to even larger and more capable language…

Computation and Language · Computer Science 2022-05-03 Barret Zoph , Irwan Bello , Sameer Kumar , Nan Du , Yanping Huang , Jeff Dean , Noam Shazeer , William Fedus

Vision Transformers have emerged as the state-of-the-art models in various Computer Vision tasks, but their high computational and resource demands pose significant challenges. While Mixture-of-Experts (MoE) can make these models more…

Computer Vision and Pattern Recognition · Computer Science 2025-05-22 Uranik Berisha , Jens Mehnert , Alexandru Paul Condurache

Despite their remarkable achievement, gigantic transformers encounter significant drawbacks, including exorbitant computational and memory footprints during training, as well as severe collapse evidenced by a high degree of parameter…

Machine Learning · Computer Science 2023-03-06 Tianlong Chen , Zhenyu Zhang , Ajay Jaiswal , Shiwei Liu , Zhangyang Wang

Sparse mixture of expert architectures (MoEs) scale model capacity without significant increases in training or inference costs. Despite their success, MoEs suffer from a number of issues: training instability, token dropping, inability to…

Machine Learning · Computer Science 2024-05-28 Joan Puigcerver , Carlos Riquelme , Basil Mustafa , Neil Houlsby

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…

Machine Learning · Computer Science 2026-01-27 Shota Takashiro , Takeshi Kojima , Shohei Taniguchi , Yusuke Iwasawa , Yutaka Matsuo

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…

Machine Learning · Computer Science 2026-02-09 Nurbek Tastan , Stefanos Laskaridis , Karthik Nandakumar , Samuel Horvath