Copertina

MAR: Efficient Large Language Models via Module-aware Architecture Refinement

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Cai, Junhong, Wang, Guiqin, Zhao, Kejie, Tang, Jianxiong, Wang, Xiang, Leng, Luziwei, Cheng, Ran, Ma, Yuxin, Guo, Qinghai
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Artificial Intelligence Computation and Language Machine Learning Neural and Evolutionary Computing
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Threshold Modulation for Online Test-Time Adaptation of Spiking Neural Networks
di: Zhao, Kejie, et al.
Pubblicazione: (2025)

SpikingMamba: Towards Energy-Efficient Large Language Models via Knowledge Distillation from Mamba
di: Huang, Yulong, et al.
Pubblicazione: (2025)

Accurate and Efficient Event-based Semantic Segmentation Using Adaptive Spiking Encoder-Decoder Network
di: Zhang, Rui, et al.
Pubblicazione: (2023)

SPikE-SSM: A Sparse, Precise, and Efficient Spiking State Space Model for Long Sequences Learning
di: Zhong, Yan, et al.
Pubblicazione: (2024)

Evolutionary Spiking Neural Networks: A Survey
di: Shen, Shuaijie, et al.
Pubblicazione: (2024)

Efficient Deep Spiking Multi-Layer Perceptrons with Multiplication-Free Inference
di: Li, Boyan, et al.
Pubblicazione: (2023)

SpikingSSMs: Learning Long Sequences with Sparse and Parallel Spiking State Space Models
di: Shen, Shuaijie, et al.
Pubblicazione: (2024)

Spatial-Temporal Search for Spiking Neural Networks
di: Che, Kaiwei, et al.
Pubblicazione: (2024)

BKDSNN: Enhancing the Performance of Learning-based Spiking Neural Networks Training with Blurred Knowledge Distillation
di: Xu, Zekai, et al.
Pubblicazione: (2024)

TMN: A Lightweight Neuron Model for Efficient Nonlinear Spike Representation
di: Gu, Yiwen, et al.
Pubblicazione: (2024)

RNC: Efficient RRAM-aware NAS and Compilation for DNNs on Resource-Constrained Edge Devices
di: Loong, Kam Chi, et al.
Pubblicazione: (2024)

Landscape-aware Automated Algorithm Design: An Efficient Framework for Real-world Optimization
di: Yin, Haoran, et al.
Pubblicazione: (2026)

SpikeAtConv: An Integrated Spiking-Convolutional Attention Architecture for Energy-Efficient Neuromorphic Vision Processing
di: Liao, Wangdan, et al.
Pubblicazione: (2024)

Enhancing Adaptive History Reserving by Spiking Convolutional Block Attention Module in Recurrent Neural Networks
di: Xu, Qi, et al.
Pubblicazione: (2024)

A Multi-objective Evolutionary Algorithm Based on Bi-population with Uniform Sampling for Neural Architecture Search
di: Xue, Yu, et al.
Pubblicazione: (2026)

SpikeZIP-TF: Conversion is All You Need for Transformer-based SNN
di: You, Kang, et al.
Pubblicazione: (2024)

ParetoTracker: Understanding Population Dynamics in Multi-objective Evolutionary Algorithms through Visual Analytics
di: Zhang, Zherui, et al.
Pubblicazione: (2024)

Tensorized NeuroEvolution of Augmenting Topologies for GPU Acceleration
di: Wang, Lishuang, et al.
Pubblicazione: (2024)

TensorNEAT: A GPU-accelerated Library for NeuroEvolution of Augmenting Topologies
di: Wang, Lishuang, et al.
Pubblicazione: (2025)

Efficient Evaluation Methods for Neural Architecture Search: A Survey
di: Song, Xiaotian, et al.
Pubblicazione: (2023)

GPU-accelerated Evolutionary Many-objective Optimization Using Tensorized NSGA-III
di: Li, Hao, et al.
Pubblicazione: (2025)

Tensorized Ant Colony Optimization for GPU Acceleration
di: Yang, Luming, et al.
Pubblicazione: (2024)

Exploring the True Potential: Evaluating the Black-box Optimization Capability of Large Language Models
di: Huang, Beichen, et al.
Pubblicazione: (2024)

A Universal Framework for Large-Scale Multi-Objective Optimization Based on Particle Drift and Diffusion
di: Li, Jia-Cheng, et al.
Pubblicazione: (2025)

EvoRL: A GPU-accelerated Framework for Evolutionary Reinforcement Learning
di: Zheng, Bowen, et al.
Pubblicazione: (2025)

Large Language Model Assisted Adversarial Robustness Neural Architecture Search
di: Zhong, Rui, et al.
Pubblicazione: (2024)

Efficient Multiplayer Battle Game Optimizer for Adversarial Robust Neural Architecture Search
di: Zhong, Rui, et al.
Pubblicazione: (2024)

Efficient Heuristics Generation for Solving Combinatorial Optimization Problems Using Large Language Models
di: Wu, Xuan, et al.
Pubblicazione: (2025)

Combining Aggregated Attention and Transformer Architecture for Accurate and Efficient Performance of Spiking Neural Networks
di: Zhang, Hangming, et al.
Pubblicazione: (2024)

Unleashing the Potential of Differential Evolution through Individual-Level Strategy Diversity
di: Feng, Chenchen, et al.
Pubblicazione: (2026)

GPU-accelerated Evolutionary Multiobjective Optimization Using Tensorized RVEA
di: Liang, Zhenyu, et al.
Pubblicazione: (2024)

Context-aware Sparse Spatiotemporal Learning for Event-based Vision
di: Wang, Shenqi, et al.
Pubblicazione: (2025)

Learning to Evolve for Optimization via Stability-Inducing Neural Unrolling
di: Gao, Jiaxin, et al.
Pubblicazione: (2025)

Evolve Cost-aware Acquisition Functions Using Large Language Models
di: Yao, Yiming, et al.
Pubblicazione: (2024)

Bridging Evolutionary Multiobjective Optimization and GPU Acceleration via Tensorization
di: Liang, Zhenyu, et al.
Pubblicazione: (2025)

Neural Architecture Search of Time-to-First-Spike-Coded Spiking Neural Networks for Efficient Eye-based Emotion Recognition
di: Liu, Qianhui, et al.
Pubblicazione: (2025)

Controlling the Mutation in Large Language Models for the Efficient Evolution of Algorithms
di: Yin, Haoran, et al.
Pubblicazione: (2024)

Scaling Behaviors of Evolutionary Algorithms on GPUs: When Does Parallelism Pay Off?
di: Yu, Xinmeng, et al.
Pubblicazione: (2026)

EvoX: A Distributed GPU-accelerated Framework for Scalable Evolutionary Computation
di: Huang, Beichen, et al.
Pubblicazione: (2023)

Migrant Resettlement by Evolutionary Multi-objective Optimization
di: Liu, Dan-Xuan, et al.
Pubblicazione: (2023)