Cover Image

Optimizing MoE Routers: Design, Implementation, and Evaluation in Transformer Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Harvey, Daniel Fidel, Weale, George, Yilmaz, Berk
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence 68T07, 68T45
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

ASNN: Learning to Suggest Neural Architectures from Performance Distributions
by: Hong, Jinwook
Published: (2025)

Explainable Image Similarity: Integrating Siamese Networks and Grad-CAM
by: Livieris, Ioannis E., et al.
Published: (2023)

Handling Out-of-Distribution Data: A Survey
by: Tamang, Lakpa, et al.
Published: (2025)

Efficient Transformations in Deep Learning Convolutional Neural Networks
by: Yilmaz, Berk, et al.
Published: (2025)

On Memory: A comparison of memory mechanisms in world models
by: Laird, Eli J., et al.
Published: (2025)

OptiRoulette Optimizer: A New Stochastic Meta-Optimizer for up to 5.3x Faster Convergence
by: Mastromichalakis, Stamatis
Published: (2026)

Overcoming Catastrophic Forgetting in Federated Class-Incremental Learning via Federated Global Twin Generator
by: Nguyen, Thinh, et al.
Published: (2024)

Transformer-Based Model for Monocular Visual Odometry: A Video Understanding Approach
by: Françani, André O., et al.
Published: (2023)

From Features to Graphs: Exploring Graph Structures and Pairwise Interactions via GNNs
by: Yamchote, Phaphontee, et al.
Published: (2025)

Influence-Inspired Spectral Rotations for Extreme Low-Bit LLM Quantization
by: Pavlov, Gorgi
Published: (2026)

On Halting vs Converging in Recurrent Graph Neural Networks
by: Bollen, Jeroen, et al.
Published: (2026)

On the Inherent Robustness of One-Stage Object Detection against Out-of-Distribution Data
by: Martinez-Seras, Aitor, et al.
Published: (2024)

TowerVision: Understanding and Improving Multilinguality in Vision-Language Models
by: Viveiros, André G., et al.
Published: (2025)

E Pluribus Unum Interpretable Convolutional Neural Networks
by: Dimas, George, et al.
Published: (2022)

Integrating Attendance Tracking and Emotion Detection for Enhanced Student Engagement in Smart Classrooms
by: Ainebyona, Keith, et al.
Published: (2026)

Building Brain Tumor Segmentation Networks with User-Assisted Filter Estimation and Selection
by: Cerqueira, Matheus A., et al.
Published: (2024)

Robust Noise Attenuation via Adaptive Pooling of Transformer Outputs
by: Brothers, Greyson
Published: (2025)

OptPO: Optimal Rollout Allocation for Test-time Policy Optimization
by: Wang, Youkang, et al.
Published: (2025)

Provable Post-Training Quantization: Theoretical Analysis of OPTQ and Qronos
by: Zhang, Haoyu, et al.
Published: (2025)

A Generalization Bound for a Family of Implicit Networks
by: Fung, Samy Wu, et al.
Published: (2024)

Deep Reinforcement Learning Xiangqi Player with Monte Carlo Tree Search
by: Yilmaz, Berk, et al.
Published: (2025)

Hybrid SIFT-SNN for Efficient Anomaly Detection of Traffic Flow-Control Infrastructure
by: Rathee, Munish, et al.
Published: (2025)

Deep learning the Hurst parameter of linear fractional processes and assessing its reliability
by: Boros, Dániel, et al.
Published: (2024)

Graph Transformers: A Survey
by: Shehzad, Ahsan, et al.
Published: (2024)

Contrastive Consolidation of Top-Down Modulations Achieves Sparsely Supervised Continual Learning
by: Tran, Viet Anh Khoa, et al.
Published: (2025)

A Language Model-Driven Semi-Supervised Ensemble Framework for Illicit Market Detection Across Deep/Dark Web and Social Platforms
by: Yazdanjue, Navid, et al.
Published: (2025)

TableMoE: Neuro-Symbolic Routing for Structured Expert Reasoning in Multimodal Table Understanding
by: Zhang, Junwen, et al.
Published: (2025)

Assessing local deformation and computing scalar curvature with nonlinear conformal regularization of decoders
by: Couéraud, Benjamin, et al.
Published: (2025)

Beyond Backpropagation: Exploring Innovative Algorithms for Energy-Efficient Deep Neural Network Training
by: Spyra, Przemysław
Published: (2025)

rETF-semiSL: Semi-Supervised Learning for Neural Collapse in Temporal Data
by: Xie, Yuhan, et al.
Published: (2025)

Flow Matching on Symmetric Spaces
by: Ruscelli, Francesco, et al.
Published: (2026)

Embracing the black box: Heading towards foundation models for causal discovery from time series data
by: Stein, Gideon, et al.
Published: (2024)

Front-propagation Algorithm: Explainable AI Technique for Extracting Linear Function Approximations from Neural Networks
by: Viaña, Javier
Published: (2024)

BrainDistill: Implantable Motor Decoding with Task-Specific Knowledge Distillation
by: Xie, Yuhan, et al.
Published: (2026)

Unveiling Memorization-Generalization Coexistence: A Case Study on Arithmetic Tasks with Label Noise
by: Liu, Linyu, et al.
Published: (2026)

TrackGPT -- A generative pre-trained transformer for cross-domain entity trajectory forecasting
by: Stroh, Nicholas
Published: (2024)

Quantum Machine Learning for Optimizing Entanglement Distribution in Quantum Sensor Circuits
by: Attisara, Laxmisha Ashok, et al.
Published: (2025)

Parameter-Efficient Transformer Embeddings
by: Ndubuaku, Henry, et al.
Published: (2025)

Reinforcement Learning for Optimizing Large Qubit Array based Quantum Sensor Circuits
by: Attisara, Laxmisha Ashok, et al.
Published: (2025)

Puzzle Similarity: A Perceptually-guided Cross-Reference Metric for Artifact Detection in 3D Scene Reconstructions
by: Hermann, Nicolai, et al.
Published: (2024)