Neural Network Compression

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

229 papers14 papers in the last four weeks, down 53% on the four weeks before. 0.1% of all new papers.

  1. OMNIS+: Semantic RAN Slicing and Quantization for Dynamic Split Neural Networks

    Nov 18, 2026Langtian Qin, Avishkar Dnyaneshwar Kawadgave, Ian Andrew Harshbarger +3Computation OffloadingWireless Resource Allocation

  2. BeFit: Shifting Complexity from Weights to Bernstein Activations for Resource-Constrained Sensing

    Nov 17, 2026Malak Gamal El-Din, Yasser Shoukry, Salma ElmalakiLightweight Neural NetworksNeural Network Hardware Acceleration

  3. Beyond a Single Sign: BiTE for Branch-Preserving Binary Threshold Expansion

    Nov 12, 2026Siddharth Gupta, Mikail Yayla, Akash KumarBinary Neural NetworksBinary Quantization

  4. A Functional Preservation Score for Auditing Connectome Operations: Compression, Alignment, Transport, and Local-Rule Writing

    Nov 10, 2026Praveg VashishthaConnectome-Informed Neural NetworksNeural Network Compression

  5. NanoNet: Ultra-Lightweight Network for MRI Brain Tumor Classification toward Edge AI

    Nov 8, 2026Tran Nguyen-Le, Huu-Thuan Huynh, Minh-Triet Tran +1Lightweight CNNsBrain Tumor Classification

  6. MINE: Entropy-coded Memory-efficient Inference for Large Language Models

    Nov 6, 2026Emil Schätzle, Markus PüschelStructured Neural Network CompressionLLM Inference Acceleration

  7. Ultra-Lightweight 3D Medical Image Segmentation via Knowledge Distillation in Label-Scarce Domains

    Nov 5, 2026Rahim Ullah, Hasan Abbas, Syed Waqar Nabi3D Medical Image SegmentationNeural Network Compression

  8. TensorSSM: Memorizing Spatial Position in Dynamic State Space for Tensor Core Generation

    Oct 29, 2026Sheng Zhang, Xinyi Wang, Maolin Wang +1Tensor DecompositionNeural Network Compression

  9. Neural Compression of Long ADMM Trajectory for Multiparametric Quadratic Program

    Oct 27, 2026Liang Wu, Honghui Zheng, Bo Yang +3Quadratic ProgrammingAlternating Direction Method of Multipliers

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

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

  11. Spike-Aware Gradient-Based Mixed-Precision Quantization of Spiking Neural Networks for Vision Applications

    Oct 21, 2026Rajshekhar Rakshit, Devgokul B., Rakshitha Kalkura +1Mixed-Precision QuantizationSpiking Neural Networks

  12. AC/DC on a Budget - Alternating Sparse Phases

    Oct 20, 2026Rahul Nittala, Advait Gadhikar, Tom Jacobs +1Neural Network CompressionNeural Network Pruning

  13. Reliability-Preserving Compression for Deployable Medical Image Segmentation

    Oct 18, 2026Sagar Kumar, Shailja Sharma, Tirthajit Baruah +1Model CompressionNeural Network Compression

  14. BitSparse: Compact Activation Storage for ReLU Feed-Forward Networks

    Oct 15, 2026Max Zhu, Bohang Sun, Pietro Lio +1Activation CompressionMemory Compression

  15. LCT: Losslessly Compressed Tensors with GPU friendly execution for Training

    Oct 15, 2026Max Zhu, Bohang Sun, Pietro Lio +1Memory CompressionMemory-Efficient Training

  16. Sparse Federated Echo State Networks for Time-Series Classification via Smooth-L1 Regularization

    Oct 15, 2026Gengcheng Lyu, Manuel Röder, Frank-Michael SchleifSparse Neural NetworksTime Series Classification

  17. Compression Through Time: An Interplay of Separability, Stationarity and Capacity

    Oct 12, 2026Nikolaus Kopp, Franz Pernkopf, Bernhard GeigerNeural Network GeneralizationRecurrent Neural Networks

  18. VLCQ: Post-training quantization for deep neural networks using variable length coding

    Oct 10, 2026Reem Abdel-Salam, Ahmed H. Abdel-Gawad, Amr G. WassalPost-Training QuantizationNeural Network Quantization

  19. The Polytopal Neural Network

    Oct 8, 2026A. Emilie J. Wedenborg, Anders V. Nørskov, Teresa Dorszewski +2Neural Network InterpretabilityGeometric Representation Learning

  20. NP-Hardness of Minimizing Neurons in Two-Hidden-Layer ReLU Neural Networks

    Oct 8, 2026Sangrock LeeReLU Neural NetworksNeural Network Approximation Theory

  21. Dynamics as Code: On Model Compression via Dynamic System

    Oct 8, 2026Fan Gao, Wei Su, Juntong Fan +4Model CompressionNeural Network Compression

  22. NeuralZip: Reusable Setup for Fast Lossless Compression

    Oct 7, 2026Martín Bravo, Samuel Horváth, Gonzalo Navarro +1Structured Neural Network CompressionLossless Data Compression

  23. CHASE: Channel-Aligned Structure Exploitation for Geometry-Aware Model Engineering

    Oct 7, 2026Wei Wang, Wei Jiang, Ziran LiuNeural Network CompressionKV-Cache Compression