Neural Network Compression

Ask about this topic

Overview

Neural network compression studies how to represent, train, or run models with fewer parameters and less memory or computation, making them practical on devices with limited resources. Common approaches include pruning weights or neurons, quantization, low-rank and tensor factorization, parameter sharing, and knowledge distillation; some methods also compress activations exchanged during distributed training. Work spans small edge models and microcontrollers as well as large language, vision, and diffusion models, evaluated on tasks such as image classification, language modeling, and video coding. A central challenge is that smaller parameter counts or fewer theoretical operations do not always mean faster inference, and aggressive compression can harm accuracy, robustness, or task-specific behavior.

Latest papers

CardsList

218 papers28 papers in the last four weeks, up 8% on the four weeks before. 0.2% of all new papers.

  1. ENEC: A Lossless AI Model Compression Method Enabling Fast Inference on Ascend NPUs

    Mar 28, 2026Jinwu Yang, Jiaan Wu, Zedong Liu +17Neural Network CompressionEfficient Neural Network Inference

    Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China · University of Chinese Academy of Sciences, Beijing, China · Huawei Technologies Co., Ltd., Shenzhen, Guangdong, China

  2. PQuantML: A Tool for End-to-End Hardware-aware Model Compression

    Mar 27, 2026Roope Niemi, Anastasiia Petrovych, Arghya Ranjan Das +9Model CompressionNeural Network Compression

    European Center for Nuclear Research (CERN), CH-1211 Geneva, Switzerland · Purdue University, West Lafayette, IN 47907, USA · California Institute of Technology, Pasadena, CA 91125, United States +4

  3. Once-for-All Channel Mixers (HYPERTINYPW): Generative Compression for TinyML

    Mar 26, 2026Yassien ShaalanNeural Network CompressionTiny ML

  4. TinyML Enhances CubeSat Mission Capabilities

    Mar 20, 2026Luigi Capogrosso, Michele MagnoOn-Device InferenceEnergy-Efficient ML

    Interdisciplinary Transformation University of Austria · ETH Zurich

  5. Growing Networks with Autonomous Pruning

    Mar 20, 2026Charles De Lambilly, Stefan DuffnerDynamic Sparse TrainingNeural Network Growth

    INSA Lyon, CNRS, Ecole Centrale de Lyon, Universite Claude Bernard Lyon 1, Université Lumière Lyon 2, LIRIS, UMR5205, , Villeurbanne, 69621, France

  6. Mix-and-Match Pruning: Globally Guided Layer-Wise Sparsification of DNNs

    Mar 17, 2026Danial Monachan, Samira Nazari, Mahdi Taheri +4Neural Network CompressionNeural Network Pruning

    Brandenburg Technical University, Cottbus, Germany · University of Zanjan, Iran · Tallinn University of Technology, Estonia +1

  7. SimCert: Probabilistic Certification for Behavioral Similarity in Deep Neural Network Compression

    Mar 16, 2026Jingyang Li, Fu Song, Guoqiang LiNeural Network VerificationNeural Network Compression

    Shanghai Jiao Tong University, Shanghai 200240, China · Institute of Software, Chinese Academy of Sciences, Beijing 100190, China

  8. High-Fidelity Compression of Seismic Velocity Models via SIREN Auto-Decoders

    Mar 15, 2026Caiyun Liu, Xiaoxue Luo, Jie XiongSinusoidal Representation NetworksModel Compression

    School of Information and Mathematics, Yangtze University, Jingzhou, Hubei 434023, P.R. China · School of Electronic Information and Electrical Engineering, Yangtze University, Jingzhou, Hubei 434023, P.R. China

  9. Adaptive MLP Pruning for Large Vision Transformers

    Mar 9, 2026Chengchao ShenNeural Network CompressionNeural Network Pruning

    Central South University

  10. Structured Multidimensional Representation Learning for Large Language Models

    Mar 5, 2026Alaa El Ichi, Khalide Jbilou, Mohamed El Guide +1TransformerEmbedding Compression

    Universit´e du Littoral Cote d’Opale, LMPA, 50 rue F. Buisson, 62228 Calais-Cedex, France. · FGSES, University Mohammed VI Polytechnic, Rabat, Morocco · LISIC, 50 rue F. Buisson, Universit´e du Littoral Cote d’Opale, 62228 Calais-Cedex, France.

  11. A Benchmark Study of Neural Network Compression Methods for Hyperspectral Image Classification

    Mar 5, 2026Sai ShiNeural Network CompressionNeural Network Quantization

    Department of Computer and Information Science, Temple University, Philadelphia, USA

  12. Causal Mechanism Reduction: Mechanism Replacement for Neural Network Pruning and Abstraction

    Feb 27, 2026Amir AsiaeeStructural Causal ModelsCausal Abstraction

    Vanderbilt University Medical Center Nashville, TN

  13. GRAIL: Post-hoc Compensation by Linear Reconstruction for Compressed Networks

    Feb 27, 2026Wenwu Tang, Dong Wang, Lothar Thiele +1Neural Network CompressionNeural Network Pruning

    Graz University of Technology · ETH Zurich, Switzerland · Complexity Science Hub, Austria

  14. Isotropic Activation Functions Enable Deindividuated Neurons and Adaptive Topologies

    Feb 26, 2026George BirdDynamic Neural NetworksNeural Network Activation Functions

    Department of Computer Science, University of Manchester, UK

  15. Compact Circulant Layers with Spectral Priors

    Feb 25, 2026Joseph Margaryan, Thomas HamelryckNeural Network CompressionBayesian Neural Networks

    Department of Computer Science (DIKU), University of Copenhagen, Copenhagen, Denmark · Department of Biology, University of Copenhagen, Copenhagen, Denmark

  16. Sensitivity-Guided Framework for Pruned and Quantized Reservoir Computing Accelerators

    Feb 24, 2026Atousa Jafari, Mahdi Taheri, Hassan Ghasemzadeh Mohammadi +2Reservoir ComputingNeural Network Compression

    Paderborn University, Paderborn, Germany · Brandenburg Technical University, Cottbus, Germany · Tallinn University of Technology, Tallinn, Estonia +1

  17. Elimination-compensation pruning for fully-connected neural networks

    Feb 24, 2026Enrico Ballini, Luca Muscarnera, Alessio Fumagalli +2Neural Network PruningNeural Network Compression

    MOX, Department of Mathematics, Politecnico di Milano, Piazza Leonardo da Vinci 32, 20133 Milano, Italy

  18. Mapping Networks

    Feb 22, 2026Lord Sen, Shyamapada MukherjeeWeight-Space LearningNeural Network Compression

    National Institute of Technology Rourkela, Odisha, India

  19. Cut Less, Fold More: Model Compression through the Lens of Projection Geometry

    Feb 20, 2026Olga Saukh, Dong Wang, Haris Šikić +2Model CompressionNeural Network Compression

    Graz University of Technology · Complexity Science Hub · Swiss Data Science Center +1

  20. Investigating Target Class Influence on Neural Network Compressibility for Energy-Autonomous Avian Monitoring

    Feb 19, 2026Nina Brolich, Simon Geis, Maximilian Kasper +3Bird Vocalization ClassificationEnergy-Efficient ML

    Fraunhofer Institute for Integrated Circuits IIS, Germany · Fachhochschule Erfurt, Germany · Universität Erfurt, Germany +2

  21. Sign Lock-In: Randomly Initialized Weight Signs Persist and Bottleneck Sub-Bit Model Compression

    Feb 19, 2026Akira Sakai, Yuma IchikawaModel CompressionNeural Network Compression

    Fujitsu Limited · Tokai University · Riken Center for AIP

  22. Amber-Image: Efficient Compression of Large-Scale Diffusion Transformers

    Feb 19, 2026Chaojie Yang, Tian Li, Yue Zhang +1Diffusion Model CompressionT2I Diffusion Models

    Computational Intelligence Dept, HelloGroup Inc.

  23. LegoNet: Memory Footprint Reduction Through Block Weight Clustering

    Feb 18, 2026Joseph Bingham, Noah Green, Saman ZonouzNeural Network Compression

    Dept of Electrical and Computer Engineering, Rutgers University, New Brunswick, New Jersey

  24. COMPOT: Calibration-Optimized Matrix Procrustes Orthogonalization for Transformers Compression

    Feb 16, 2026Denis Makhov, Dmitriy Shopkhoev, Magauiya Zhussip +3Orthogonal Procrustes AlignmentModel Compression

    Fundamental Research Center MWS AI · ITMO

  25. Algorithmic Simplification of Neural Networks with Mosaic-of-Motifs

    Feb 16, 2026Pedram Bakhtiarifard, Tong Chen, Jonathan Wenshøj +2Kolmogorov ComplexityNeural Network Compression

    Department of Computer Science, University of Copenhagen, Denmark

  26. RNM-TD3: N:M Semi-structured Sparse Reinforcement Learning From Scratch

    Feb 16, 2026Isam Vrce, Andreas Kassler, Gökçe AydosStructured SparsityNeural Network Compression

    Deggendorf Institute of Technology, Dieter-Görlitz-Platz 1, Deggendorf, Germany · Department of Engineering Technology, Technical University of Denmark, Ballerup, Denmark

  27. Exploiting heterogeneous delays for efficient computation in low-bit neural networks

    Oct 31, 2025Pengfei Sun, Jascha Achterberg, Zhe Su +2Neuromorphic ComputingSpiking Neural Networks

    Department of Electrical and Electronic Engineering, Imperial College London. · Centre for Neural Circuits and Behaviour, University of Oxford. · Institute of Neuroinformatics, University of Zurich and ETH Zurich. +2

  28. Real-Time Neural Video Compression with Unified Intra and Inter Coding

    Oct 16, 2025Hui Xiang, Yifan Bian, Li Li +3Learned Image CompressionNeural Video Compression

    University of Science and Technology of China · Tencent Shannon Lab

  29. BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression

    Sep 29, 2025David González-MartínezLow-Rank Matrix DecompositionLow-Rank Compression

    Department of Computer Science and Artificial Intelligence, Universidad de Sevilla · Tübingen AI Center

  30. On the Interaction of Compressibility and Adversarial Robustness

    Jul 23, 2025Melih Barsbey, Antônio H. Ribeiro, Umut Şimşekli +1Neural Network RobustnessAdversarial Robustness

    Department of Computing, Imperial College London, UK · Department of Information Technology, Uppsala University, Sweden · INRIA, CNRS, Département d’Informatique de l’Ecole Normale Supérieure / PSL, France