Structured Pruning

Ask about this topic

Overview

Structured pruning reduces a network by removing hardware-friendly components such as convolutional channels, transformer heads and layers, or mixture-of-experts neurons. Methods rank components using signals such as activation magnitude, gradients, Fisher or Hessian estimates, and task-specific sensitivity, then allocate removals under parameter, memory, or latency budgets. Fine-tuning, distillation, and weight compensation can recover lost performance, while newer approaches target language, vision-language, and generative models as well as smaller vision networks. A central challenge is that high sparsity or fewer FLOPs do not guarantee preserved task quality or real speedups: results depend on calibration data, model structure, recovery cost, and the hardware and kernels used at deployment.

Latest papers

CardsList

66 papers11 papers in the last four weeks, up 83% on the four weeks before. 0.1% of all new papers.

  1. DAC-Loop: Distillation-Aware Compression for Remote Sensing CNN

    Oct 26, 2026Rico Staedeli, Lorena Raichle, Konstantinos Tzevelekakis +2Neural Network CompressionNeural Network Pruning

    AIML Lab, School of Computer Science, University of St. Gallen

  2. Unlocking the Specialization Capability of PPG Foundation Models for Wearable Signals through Structured Pruning and Adaptive Fine-Tuning

    Oct 24, 2026Huaming Du, Zhixian Xie, Gaoyang Zhen +6Time-Series Foundation ModelsStructured Pruning

    Southwestern University of Finance and Economics · Jizhi Technology Co., Ltd. · Fuzhou University +2

  3. Fine-Grained Units, Flat Decisions: Hierarchical Micro-Expert Pruning for Mixture-of-Experts Models

    Oct 19, 2026Zukang Xu, Xinpei Gao, Xing Hu +2Channel PruningMixture-of-Experts Pruning

    Houmo AI · University of Science and Technology of China · Southeast University

  4. BMuon: Budgeting Muon's Spectral Geometry for Structured Compressibility

    Oct 16, 2026Rida Assalouh, Tom Jacobs, Rebekka Burkholz +2Muon OptimizerStructured Sparsity

    Inria, Paris, France · ´Ecole polytechnique, Institut Polytechnique de Paris, Palaiseau, France · CISPA Helmholtz Center for Information Security, Saarbrücken, Germany +3

  5. Replay Pruning and Few-Bit Integer Inference for Hardware-Efficient Speed-Sign Recognition

    Oct 16, 2026Se Un Park, Kyungkeon Chung, Huigeol Kim +1Channel PruningEfficient Inference

    UX Factory, Inc. · BTree Co., Ltd.

  6. Your Transformer Is Secretly Elastic

    Oct 14, 2026Walter Simoncini, Dheeraj Varghese, Gertjan J. Burghouts +1Elastic Neural NetworksTransformer Pruning

    University of Amsterdam · TNO, Intelligent Imaging

  7. Carve VFM: Carving Specialists out of Generalists, Automatic Task-Specific Compression of Vision Foundation Models

    Oct 12, 2026Lotfi Abdelkrim Mecharbat, Abdelrahman Elsayed, Ibrahim Almakky +2Model CompressionNeural Network Pruning

    Mohamed bin Zayed University of Artificial Intelligence

  8. Heterogeneous Structured Pruning Under Resource Constraints for Hardware-Efficient Large Language Models

    Oct 11, 2026Cameron Barker, Andreas Paraskeva, Jan N. van Rijn +2LLM PruningNeural Network Pruning

    School of Informatics, University of Edinburgh, UK · Leiden Institute of Advanced Computer Science, Leiden University, the Netherlands · School of Engineering, University of Edinburgh, UK

  9. SARATHI: Decoupled Data-Free Probing and Adaptive Reconstruction for Structured LLM Pruning

    Oct 11, 2026Sankar Behera, Dhruv Singh, Satyadev Ahlawat +1LLM PruningStructured Pruning

    Department of Computer Science and Engineering, IIT Jammu · Department of Mathematics, IIT Jammu · Department of Electrical Engineering, IIT Jammu

  10. WUSPruner: Second-Moment-Optimal Transforms for Structured Pruning

    Oct 11, 2026Shengkun Tang, Dan Alistarh, Zhiqiang ShenLLM PruningStructured Pruning

    MBZUAI · ISTA

  11. Exploring the Trade-Off Between Structured Pruning and Fault Tolerance in Deep Neural Networks for Space Applications

    Oct 2, 2026Toon Vinck, Naïn Jonckers, Jaro De Roose +2Neural Network RobustnessStructured Pruning

    Magics Technologies, Geel, Belgium · ESAT-ADVISE, KU Leuven, Geel, Belgium · Dept. of Computer Science, Leuven.AI, KU Leuven, Leuven, Belgium +1

  12. FedSAP: Federated Learning with Structured Adaptive Partitioning for Multi-Domain Heterogeneous Edge Devices

    Oct 1, 2026Wentao Yue, Tianyou Lai, Hongji Li +2Non-IID Federated LearningFederated Domain Generalization

  13. Resource-Aware Federated Mixture-of-Experts with Adaptive Pruning for Onboard Learning in LEO Satellite Constellations

    Sep 25, 2026Mohamed Shaaban, Mohamed Elmahallawy, Marius Bernahrndt +1Federated LearningMixture of Experts

    School of Engineering and Applied Science, Washington State University, Richland, WA 99354, USA · Institute for Software Technology, German Aerospace Center (DLR), Porz, 51147 Cologne, Germany

  14. Unified Response Geometry for Structured Pruning

    Sep 16, 2026Kaixiang ShuStructured PruningNeural Network Pruning

    Independent Researcher

  15. LILA: Calibration-Free Structured Pruning of Large Language Models via Latent Spectral Geometry

    Sep 10, 2026Sankar Behera, Dhruv Singh, Anshika Agnihotri +3LLM PruningLLM Compression

    CSE, IIT Jammu · Mathematics, IIT Jammu · IT, EC Bikaner +1

  16. Dense Structural Compression of Transformers via Gauge-Correct Channel Removal

    Sep 7, 2026Jed A. Duersch, Naïm Es-Sebbani, Nathanaël Haas +1Efficient Transformer InferenceChannel Pruning

    Université d’Artois, CNRS, CRIL UMR 8188, Lens, France

  17. Train Overcomplete, Deploy Compact: Scaling Recovery Capacity for Structured LLM Pruning

    Sep 7, 2026Seungmin Oh, Donggeon Lee, Jongbin RyuLLM PruningLLM Compression

    Ajou University, South Korea

  18. Functional Degeneracy in Neural Networks: Measurement and Pruning

    Aug 31, 2026Maria Matveev, Pascal Esser, Ayush Bharadwaj +2Structured PruningNeural Network Compression

    Department of Mathematics, LMU Munich · Munich Center for Machine Learning (MCML) · Independent +3

  19. PruneShift: A Framework for Evaluating Decision Reliability in Structured Pruning

    Aug 30, 2026Hao Ye, Gaopeng ZhangSurrogate ModelingStructured Pruning

    Xi’an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences · University of Chinese Academy of Sciences

  20. Task-Aware Spectral Pruning: A Mixture-of-Masks Framework for Efficient LLM Inference

    Aug 24, 2026Ibne Farabi Shihab, Fariya Afrin, Sanjeda Akter +1LLM PruningLLM Inference Acceleration

    Department of Computer Science, Iowa State University · Department of Computer Science, Kalinga Institute of Industrial Technology · Department of Civil, Construction & Environmental Engineering, Iowa State University

  21. COEC: Calibrated Orthogonal-Equivalence Compensation for Structured Pruning of Large Language Models

    Aug 21, 2026Peiqi Yu, Nam Ling, Wei Wang +1LLM PruningLLM Compression

    School of Engineering, Santa Clara University, Santa Clara, CA, USA · Futurewei Technologies, Inc., USA

  22. Unifying Depth and Width Pruning for LLMs via Binary Knapsack Optimization

    Aug 13, 2026Palaash Goel, Ayan Sengupta, Akshay Nambi +1LLM PruningStructured Pruning

    Yardi School of Artificial Intelligence, Indian Institute of Technology Delhi · Department of Electrical Engineering, Indian Institute of Technology Delhi · Microsoft Research (MSR) India

  23. InterPruner: Interactive Structured Pruning via Taylor-Implicit Criterion and Language-Prior Modulator for Multimodal Object Detection

    Aug 11, 2026Qi Ming, Zihan Yang, Shaoguang Huang +6Multispectral Object DetectionInfrared Object Detection

    Beijing University of Technology · Southwest University · China University of Geosciences Wuhan +5

  24. StaticSegFormer: An Efficient High-Performance Semantic Segmentation Based on Static Structured Pruning

    Aug 5, 2026Timo Bartels, Danish Nazir, Jan Piewek +2Efficient Neural Network InferenceStructured Pruning

    Technische Universität Braunschweig, Germany · Group Innovation, Volkswagen AG, Wolfsburg, Germany

  25. SlimVLM: Sensitivity-aware Dynamic Structured Pruning with Adaptive Visual Token Selection for Efficient Vision-Language Models

    Aug 4, 2026Yaozhi Wen, Jialong Guo, Zhenliang Ni +2Efficient VLM InferenceStructured Pruning

    Huawei Technologies

  26. CoCurve: Cross-Module Co-Pruning Curvature for Training-Free Structured LLM Pruning

    Jul 20, 2026Zhiren Gong, Zihao Zeng, Zijie Wang +3LLM PruningLLM Compression

    College of Computing and Data Science, Nanyang Technological University, Singapore · Interdisciplinary Graduate Programme, Nanyang Technological University, Singapore · School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore

  27. Structured Pruning of Large Language Models via Power Transformation and Sign-Preserving Score Aggregation with Adaptive Feature Retention

    Jul 9, 2026Ryota Kobayashi, Tsubasa Hirakawa, Takayoshi Yamashita +4LLM PruningLLM Compression

    1Chubu University · 2Panasonic Holdings Corporation

  28. FlexMoE: One-for-All Nested Intra-Expert Pruning for MoE Language Models

    Jun 26, 2026Fan Mo, Yuxuan Han, Geng Zhang +2Mixture-of-Experts PruningLLM Pruning

    National University of Singapore

  29. Drop-Then-Recovery: How Redundant Are Vision-Language-Action Models?

    Jun 26, 2026Guoheng Sun, Kaixi Feng, Shwai He +8Model CompressionEfficient VLA Models

    University of Maryland, College Park · 2Cisco Research

  30. Cascaded Multi-Granularity Pruning for On-Device LLM Inference in Industrial IoT

    Jun 25, 2026Jinghan Wang, Yanjun Chen, Wei Zhang +3LLM PruningOn-Device Language Model Inference

    School of Mechanical and Electrical Engineering, Harbin Institute of Technology, Harbin 150001, China · School of Information Science and Technology, Eastern Institute of Technology, Ningbo, China