Image de couverture de livre

Union of Experts: Adapting Hierarchical Routing to Equivalently Decomposed Transformer

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Yang, Yujiao, Lian, Jing, Li, Linhui
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Artificial Intelligence Computation and Language 68T07 I.5.1; I.2.0
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Deceptive Diffusion: Generating Synthetic Adversarial Examples
par: Beerens, Lucas, et autres
Publié: (2024)

The First MPDD Challenge: Multimodal Personality-aware Depression Detection
par: Fu, Changzeng, et autres
Publié: (2025)

DecompKAN: Decomposed Patch-KAN for Long-Term Time Series Forecasting
par: Mysore, Naveen
Publié: (2026)

JacNet: Learning Functions with Structured Jacobians
par: Lorraine, Jonathan, et autres
Publié: (2024)

Closing the Theory-Practice Gap in Spiking Transformers via Effective Dimension
par: Guo, Dongxin, et autres
Publié: (2026)

PolyGLU: State-Conditional Activation Routing in Transformer Feed-Forward Networks
par: Medeiros, Daniel Nobrega
Publié: (2026)

Which Transformer to Favor: A Comparative Analysis of Efficiency in Vision Transformers
par: Nauen, Tobias Christian, et autres
Publié: (2023)

A Hybrid Inductive-Transductive Network for Traffic Flow Imputation on Unsampled Locations
par: Rahimiasl, Mohammadmahdi, et autres
Publié: (2025)

multivariateGPT: a decoder-only transformer for multivariate categorical and numeric data
par: Loza, Andrew J., et autres
Publié: (2025)

Scaling Laws in the Tiny Regime: How Small Models Change Their Mistakes
par: Alnemari, Mohammed, et autres
Publié: (2026)

A Boltzmann-machine-enhanced Transformer For DNA Sequence Classification
par: Cao, Zhixuan, et autres
Publié: (2026)

CVCM Track Circuits Pre-emptive Failure Diagnostics for Predictive Maintenance Using Deep Neural Networks
par: Mukherjee, Debdeep, et autres
Publié: (2025)

CellARC: Measuring Intelligence with Cellular Automata
par: Lžičař, Miroslav
Publié: (2025)

AssistedDS: Benchmarking How External Domain Knowledge Assists LLMs in Automated Data Science
par: Luo, An, et autres
Publié: (2025)

GradES: Significantly Faster Training in Transformers with Gradient-Based Early Stopping
par: Wen, Qifu, et autres
Publié: (2025)

Explicit Dropout: Deterministic Regularization for Transformer Architectures
par: Agrawal, Vidhi, et autres
Publié: (2026)

Efficient Morphology-Control Co-Design via Stackelberg Proximal Policy Optimization
par: Dai, Yanning, et autres
Publié: (2026)

GRALIS: A Unified Canonical Framework for Linear Attribution Methods via Riesz Representation
par: Fanale, Raimondo
Publié: (2026)

Can Agentic AI Match the Performance of Human Data Scientists?
par: Luo, An, et autres
Publié: (2025)

AgentDS Technical Report: Benchmarking the Future of Human-AI Collaboration in Domain-Specific Data Science
par: Luo, An, et autres
Publié: (2026)

Optimizing Inference in Transformer-Based Models: A Multi-Method Benchmark
par: Ho, Siu Hang, et autres
Publié: (2025)

Neural Conditional Transport Maps
par: Rodriguez-Pardo, Carlos, et autres
Publié: (2025)

TaylorShift: Shifting the Complexity of Self-Attention from Squared to Linear (and Back) using Taylor-Softmax
par: Nauen, Tobias Christian, et autres
Publié: (2024)

KAN vs LSTM Performance in Time Series Forecasting
par: Rather, Tabish Ali, et autres
Publié: (2025)

H-Model: Dynamic Neural Architectures for Adaptive Processing
par: Hospodarchuk, Dmytro
Publié: (2025)

Scalable, Technology-Agnostic Diagnosis and Predictive Maintenance for Point Machine using Deep Learning
par: Di Santi, Eduardo, et autres
Publié: (2025)

DeepDRK: Deep Dependency Regularized Knockoff for Feature Selection
par: Shen, Hongyu, et autres
Publié: (2024)

InhibiDistilbert: Knowledge Distillation for a ReLU and Addition-based Transformer
par: Zhang, Tony, et autres
Publié: (2025)

Revisiting GAN with Bayes-Optimal Discrimination
par: Naeini, Mohammadreza Tavasoli, et autres
Publié: (2025)

Complex-Valued Phase-Coherent Transformer
par: Hioki, Leona
Publié: (2026)

PH-VAE: A Polynomial Hierarchical Variational Autoencoder Towards Disentangled Representation Learning
par: Chen, Xi, et autres
Publié: (2025)

Revisiting Non-separable Binary Classification and its Applications in Anomaly Detection
par: Lau, Matthew, et autres
Publié: (2023)

Few-Class Arena: A Benchmark for Efficient Selection of Vision Models and Dataset Difficulty Measurement
par: Cao, Bryan Bo, et autres
Publié: (2024)

mlx-snn: Spiking Neural Networks on Apple Silicon via MLX
par: Qin, Jiahao
Publié: (2026)

Massive Redundancy in Gradient Transport Enables Sparse Online Learning
par: Merin, Aur Shalev
Publié: (2026)

SigGate-GT: Taming Over-Smoothing in Graph Transformers via Sigmoid-Gated Attention
par: Guo, Dongxin, et autres
Publié: (2026)

Transfer learning with generative models for object detection on limited datasets
par: Paiano, Matteo, et autres
Publié: (2024)

Pulse-Driven Neural Architecture: Learnable Oscillatory Dynamics for Robust Continuous-Time Sequence Processing
par: Sharma, Paras
Publié: (2026)

GraphNNK -- Graph Classification and Interpretability
par: Bolevic, Zeljko, et autres
Publié: (2026)

Temporal Functional Circuits: From Spline Plots to Faithful Explanations in KAN Forecasting
par: Mysore, Naveen
Publié: (2026)