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

• URL: http://arxiv.org/abs/2601.21503v1
• Date: Thu, 29 Jan 2026 10:21:28 GMT
• Title: MAR: Efficient Large Language Models via Module-aware Architecture Refinement
• Authors: Junhong Cai, Guiqin Wang, Kejie Zhao, Jianxiong Tang, Xiang Wang, Luziwei Leng, Ran Cheng, Yuxin Ma, Qinghai Guo,
• Abstract summary: Large Language Models (LLMs) excel across diverse domains but suffer from high energy costs due to quadratic attention and dense Feed-Forward Network (FFN) operations.<n>We propose Module-aware Architecture Refinement (MAR), a framework that integrates State Space Models (SSMs) for linear-time sequence modeling and applies activation sparsification to reduce FFN costs.
• Score: 27.413577161712876
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large Language Models (LLMs) excel across diverse domains but suffer from high energy costs due to quadratic attention and dense Feed-Forward Network (FFN) operations. To address these issues, we propose Module-aware Architecture Refinement (MAR), a two-stage framework that integrates State Space Models (SSMs) for linear-time sequence modeling and applies activation sparsification to reduce FFN costs. In addition, to mitigate low information density and temporal mismatch in integrating Spiking Neural Networks (SNNs) with SSMs, we design the Adaptive Ternary Multi-step Neuron (ATMN) and the Spike-aware Bidirectional Distillation Strategy (SBDS). Extensive experiments demonstrate that MAR effectively restores the performance of its dense counterpart under constrained resources while substantially reducing inference energy consumption. Furthermore, it outperforms efficient models of comparable or even larger scale, underscoring its potential for building efficient and practical LLMs.

Related papers

• MS-SSM: A Multi-Scale State Space Model for Efficient Sequence Modeling [60.648359990090846]
  State-space models (SSMs) have recently attention as an efficient alternative to computationally expensive attention-based models for sequence modeling.<n>This paper introduces a multi-scale SSM framework that represents sequence dynamics across multiple resolution and processing each resolution with specialized state-space dynamics.
  arXiv  Detail & Related papers  (2025-12-29T19:36:28Z)
• LatentLLM: Attention-Aware Joint Tensor Compression [50.33925662486034]
  Large language models (LLMs) and large multi-modal models (LMMs) require a massive amount of computational and memory resources.<n>We propose a new framework to convert such LLMs/LMMs into a reduced-dimension latent structure.
  arXiv  Detail & Related papers  (2025-05-23T22:39:54Z)
• Distillation-Supervised Convolutional Low-Rank Adaptation for Efficient Image Super-Resolution [19.22142805041799]
  Convolutional neural networks (CNNs) have been widely used in efficient image super-resolution.<n>We propose Distillation-Supervised Convolutional Low-Rank Adaptation (DSCLoRA), which improves model performance without increasing architectural complexity or inference costs.
  arXiv  Detail & Related papers  (2025-04-15T15:12:57Z)
• DSMoE: Matrix-Partitioned Experts with Dynamic Routing for Computation-Efficient Dense LLMs [86.76714527437383]
  This paper proposes DSMoE, a novel approach that achieves sparsification by partitioning pre-trained FFN layers into computational blocks.<n>We implement adaptive expert routing using sigmoid activation and straight-through estimators, enabling tokens to flexibly access different aspects of model knowledge.<n>Experiments on LLaMA models demonstrate that under equivalent computational constraints, DSMoE achieves superior performance compared to existing pruning and MoE approaches.
  arXiv  Detail & Related papers  (2025-02-18T02:37:26Z)
• Explore Activation Sparsity in Recurrent LLMs for Energy-Efficient Neuromorphic Computing [3.379854610429579]
  Recurrent Large Language Models (R-LLM) have proven effective in mitigating the complexity of self-attention.<n>We propose a low-cost, training-free algorithm to sparsify R-LLMs' activations to enhance energy efficiency on neuromorphic hardware.
  arXiv  Detail & Related papers  (2025-01-09T19:13:03Z)
• Pruning Large Language Models to Intra-module Low-rank Architecture with Transitional Activations [21.229296254354878]
  We introduce a task-agnostic structured pruning approach coupled with a compact Transformer architecture design. The proposed approach, named TransAct, reduces transitional activations inside multi-head attention (MHA) and multi-layer perceptron (MLP) modules. Results verify the optimality of our approach at high compression with respect to both efficiency and performance.
  arXiv  Detail & Related papers  (2024-07-08T07:45:38Z)
• Not All Attention is Needed: Parameter and Computation Efficient Transfer Learning for Multi-modal Large Language Models [73.48675708831328]
  We propose a novel parameter and computation efficient tuning method for Multi-modal Large Language Models (MLLMs) The Efficient Attention Skipping (EAS) method evaluates the attention redundancy and skips the less important MHAs to speed up inference. The experiments show that EAS not only retains high performance and parameter efficiency, but also greatly speeds up inference speed.
  arXiv  Detail & Related papers  (2024-03-22T14:20:34Z)
• ECoFLaP: Efficient Coarse-to-Fine Layer-Wise Pruning for Vision-Language Models [70.45441031021291]
  Large Vision-Language Models (LVLMs) can understand the world comprehensively by integrating rich information from different modalities. LVLMs are often problematic due to their massive computational/energy costs and carbon consumption. We propose Efficient Coarse-to-Fine LayerWise Pruning (ECoFLaP), a two-stage coarse-to-fine weight pruning approach for LVLMs.
  arXiv  Detail & Related papers  (2023-10-04T17:34:00Z)
• Sparse Modular Activation for Efficient Sequence Modeling [94.11125833685583]
  Recent models combining Linear State Space Models with self-attention mechanisms have demonstrated impressive results across a range of sequence modeling tasks. Current approaches apply attention modules statically and uniformly to all elements in the input sequences, leading to sub-optimal quality-efficiency trade-offs. We introduce Sparse Modular Activation (SMA), a general mechanism enabling neural networks to sparsely activate sub-modules for sequence elements in a differentiable manner.
  arXiv  Detail & Related papers  (2023-06-19T23:10:02Z)
• IMDeception: Grouped Information Distilling Super-Resolution Network [7.6146285961466]
  Single-Image-Super-Resolution (SISR) is a classical computer vision problem that has benefited from the recent advancements in deep learning methods. In this work, we propose the Global Progressive Refinement Module (GPRM) as a less parameter-demanding alternative to the IIC module for feature aggregation. We also propose Grouped Information Distilling Blocks (GIDB) to further decrease the number of parameters and floating point operations persecond (FLOPS) Experiments reveal that the proposed network performs on par with state-of-the-art models despite having a limited number of parameters and FLOPS
  arXiv  Detail & Related papers  (2022-04-25T06:43:45Z)
• Optimization-driven Machine Learning for Intelligent Reflecting Surfaces Assisted Wireless Networks [82.33619654835348]
  Intelligent surface (IRS) has been employed to reshape the wireless channels by controlling individual scattering elements' phase shifts. Due to the large size of scattering elements, the passive beamforming is typically challenged by the high computational complexity. In this article, we focus on machine learning (ML) approaches for performance in IRS-assisted wireless networks.
  arXiv  Detail & Related papers  (2020-08-29T08:39:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.