English
Related papers

Related papers: Learning to Route Among Specialized Experts for Ze…

200 papers

Modern large language models leverage Mixture-of-Experts (MoE) architectures for efficient scaling, but face a critical challenge: functionally similar experts are often selected simultaneously, creating redundant computation and limiting…

Computation and Language · Computer Science 2025-10-16 Chen Zheng , Yuhang Cai , Deyi Liu , Jin Ma , Yiyuan Ma , Yuan Yang , Jing Liu , Yutao Zeng , Xun Zhou , Siyuan Qiao

Sparse Mixture-of-Experts (MoE) architectures route each token through a subset of experts at each layer independently. We propose viewing MoE computation through the lens of \emph{expert paths} -- the sequence of expert selections a token…

Machine Learning · Computer Science 2026-04-07 Zijin Gu , Tatiana Likhomanenko , Vimal Thilak , Jason Ramapuram , Navdeep Jaitly

Mixture-of-Experts (MoE) benefits from a dynamic routing mechanism among their specialized experts, which existing Parameter- Efficient Fine-Tuning (PEFT) strategies fail to leverage. This motivates us to investigate whether adaptation…

Machine Learning · Computer Science 2025-08-05 Yilun Liu , Yunpu Ma , Yuetian Lu , Shuo Chen , Zifeng Ding , Volker Tresp

Mixture-of-Experts (MoE) has become the dominant architecture for scaling large language models: frontier models routinely decouple total parameters from per-token computation through sparse expert routing. Scaling laws show that under…

Machine Learning · Computer Science 2026-05-12 Chaitanya Dwivedi , Binxuan Huang , Himanshu Gupta , Pratik Jayarao , Neeraj Varshney , Bing Yin

Adapting pre-trained vision models using parameter-efficient fine-tuning (PEFT) remains challenging, as it aims to achieve performance comparable to full fine-tuning using a minimal number of trainable parameters. When applied to complex…

Computer Vision and Pattern Recognition · Computer Science 2026-05-21 Meng Lou , Stanley Yu , Yizhou Yu

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

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 sparse Mixture-of-Experts (Sparse-MoE) framework efficiently scales up model capacity in various domains, such as natural language processing and vision. Sparse-MoEs select a subset of the "experts" (thus, only a portion of the overall…

Machine Learning · Computer Science 2023-06-06 Shibal Ibrahim , Wenyu Chen , Hussein Hazimeh , Natalia Ponomareva , Zhe Zhao , Rahul Mazumder

Efficiency, specialization, and adaptability to new data distributions are qualities that are hard to combine in current Large Language Models. The Mixture of Experts (MoE) architecture has been the focus of significant research because its…

Computation and Language · Computer Science 2024-08-29 Nikolas Gritsch , Qizhen Zhang , Acyr Locatelli , Sara Hooker , Ahmet Üstün

This study investigates the behavior of model-integrated routers in Mixture of Experts (MoE) models, focusing on how tokens are routed based on their linguistic features, specifically Part-of-Speech (POS) tags. The goal is to explore across…

Computation and Language · Computer Science 2024-12-24 Elie Antoine , Frédéric Béchet , Philippe Langlais

Mixture-of-Experts (MoE) models are designed to enhance the efficiency of large language models (LLMs) without proportionally increasing the computational demands. However, their deployment on edge devices still faces significant challenges…

Machine Learning · Computer Science 2024-08-21 Shuzhang Zhong , Ling Liang , Yuan Wang , Runsheng Wang , Ru Huang , Meng Li

Mixture-of-Experts (MoE) layers increase model capacity by activating only a small subset of experts per token, and typically rely on a learned router to map hidden states to expert assignments. In this work, we ask whether a dedicated…

Artificial Intelligence · Computer Science 2026-04-02 Jama Hussein Mohamud , Drew Wagner , Mirco Ravanelli

By routing input tokens to only a few split experts, Sparse Mixture-of-Experts has enabled efficient training of large language models. Recent findings suggest that fixing the routers can achieve competitive performance by alleviating the…

We focus on multi-domain Neural Machine Translation, with the goal of developing efficient models which can handle data from various domains seen during training and are robust to domains unseen during training. We hypothesize that Sparse…

Computation and Language · Computer Science 2024-07-02 Nadezhda Chirkova , Vassilina Nikoulina , Jean-Luc Meunier , Alexandre Bérard

Most unsupervised anomaly detection methods based on representations of normal samples to distinguish anomalies have recently made remarkable progress. However, existing methods only learn a single decision boundary for distinguishing the…

Computer Vision and Pattern Recognition · Computer Science 2024-09-10 Tianwu Lei , Silin Chen , Bohan Wang , Zhengkai Jiang , Ningmu Zou

Mixture-of-Experts (MoE) models mostly use a router to assign tokens to specific expert modules, activating only partial parameters and often outperforming dense models. We argue that the separation between the router's decision-making and…

Computation and Language · Computer Science 2025-06-02 Ang Lv , Ruobing Xie , Yining Qian , Songhao Wu , Xingwu Sun , Zhanhui Kang , Di Wang , Rui Yan

Large pretrained Transformer language models have been shown to exhibit zero-shot generalization, i.e. they can perform a wide variety of tasks that they were not explicitly trained on. However, the architectures and pretraining objectives…

Computation and Language · Computer Science 2022-04-13 Thomas Wang , Adam Roberts , Daniel Hesslow , Teven Le Scao , Hyung Won Chung , Iz Beltagy , Julien Launay , Colin Raffel

Mixture-of-Experts models enable large language models to scale efficiently, as they only activate a subset of experts for each input. Their core mechanisms, Top-k routing and auxiliary load balancing, remain heuristic, however, lacking a…

Machine Learning · Computer Science 2026-01-08 Ye Su , Yong Liu

Mixture of Experts (MoE) models enable parameter-efficient scaling through sparse expert activations, yet optimizing their inference and memory costs remains challenging due to limited understanding of their specialization behavior. We…

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

This article focuses on large language models (LLMs) fine-tuning in the scarce data regime (also known as the "few-shot" learning setting). We propose a method to increase the generalization capabilities of LLMs based on neural network…

Machine Learning · Computer Science 2023-10-25 Louis Falissard , Vincent Guigue , Laure Soulier