Neural Network Quantization

Ask about this topic

Overview

Neural network quantization studies how to use lower-precision numbers for model weights, activations, caches, and training states while preserving useful behavior. Post-training quantization adjusts a trained model using calibration data or reconstruction objectives, while quantization-aware training exposes the model to low precision during optimization; rotations, outlier handling, and mixed-precision allocation are common techniques. Work spans language models and KV caches, vision and diffusion models, and edge devices, with quality measured using benchmarks such as ImageNet, language-model perplexity, reasoning tasks, and generative quality. A central tension is that lower bit widths do not guarantee faster or safer deployment: accuracy and behavior can shift, and real gains depend on hardware, kernels, and the task being evaluated.

Latest papers

CardsList

405 papers64 papers in the last four weeks, up 42% on the four weeks before. 0.4% of all new papers.

  1. The Role of Quantization in Loss Spikes

    Oct 28, 2026Zaiqian Chen, Aditya Somasundaram, Sophie Li +4LLM TrainingLanguage Model Pretraining

    Columbia University · Mohamed bin Zayed University of Artificial Intelligence · University of Maryland +1

  2. AxisQ: Depth-Adaptive Channel--Frequency Quantization for Camouflaged Object Detection

    Oct 27, 2026Chi Ruan, Tianqi Li, Xin He +3Post-Training QuantizationAdaptive Quantization

    SpinEntropy · Nankai University · Tianjin University of Technology +1

  3. A Resource-Efficient and Precision-Scalable FPGA Accelerator for Spiking Neural Networks Using Minifloat Arithmetic

    Oct 23, 2026Ali Mehrabi, Philip C. JoseFPGA-Based Neural Network AccelerationSpiking Neural Networks

    School of Engineering, Computing, and Science, Western Sydney University, Sydney, Australia

  4. Every Weight Is a Path of Shared Discrete Decisions

    Oct 22, 2026Ammar Ali, Stamatis LefkimmiatisNeural Network CompressionNeural Network Hardware Acceleration

    LEAD Lab, ITMO University

  5. Different Tasks, Different Timesteps: Temporal Task-Aware Quantization for Diffusion Language Models

    Oct 22, 2026Ofek Avivi, Eliron Rahimi, Avi Mendelson +1Neural Network QuantizationMixed-Precision Quantization

    Technion – Israel Institute of Technology · INSIGHT Lab, Ben-Gurion University of the Negev

  6. TernScope: Model-Hardware Co-Design for Efficient Ternary Endoscopic Segmentation

    Oct 21, 2026Zhuoyu Wu, Wenhui Ou, Qiawei Zheng +3Medical Image SegmentationNeural Network Hardware Acceleration

    CyPhi AI Research Lab, School of Information Technology, Monash University Malaysia, Malaysia · Department of Electronic and Computer Engineering, The Hong Kong University of Science and Technology, Hong Kong · School of Computer Science and Engineering, Southeast University, Nanjing, China +1

  7. PACE: Periodic and Channel-Aligned Encoding of Four-Bit Recurrent States

    Oct 21, 2026Patrick Haller, Filipe Laitenberger, Alan AkbikRecurrent-State QuantizationLLM Quantization

    Humboldt-Universität zu Berlin

  8. When PTQ Calibration Helps or Hurts: Dose-Driven Collapse and Validation-Gated Abstention in Quantized Text Embedders

    Oct 19, 2026Hyojung Han, Ryangkyung Kang, Youngeun Kim +1Post-Training QuantizationNeural Network Quantization

    ThakiCloud · Korea University

  9. Compiling Multi-Threshold Operators for Quantized Non-Monotonic and Fine-Granular Activations in Custom-Tailored DNN Accelerators

    Oct 15, 2026Christoph Berganski, Felix Jentzsch, Marco PlatznerActivation QuantizationNeural Network Activation Functions

    Computer Engineering Group, Paderborn University, Paderborn, Germany

  10. RoleQ: Role-Aligned Scales for Converting Language Models to Ternary

    Oct 15, 2026Johannes Knittel, Alec Helbling, Hanspeter PfisterLLM QuantizationNeural Network Quantization

    Harvard University · Georgia Tech

  11. ShiftQAT: Quantization-Aware Training for the Numerical Contract of a Fixed-Function Edge CNN Accelerator

    Oct 15, 2026Oguzhan Buyuksolak, Osman Erman Okman, Mehmet Gorkem UlkarHardware-Aware QuantizationNeural Network Quantization

    Analog Devices, Inc.

  12. Fractional Power-of-Two Quantization for Efficient and Effective Multiplier-Free LLM Inference

    Oct 15, 2026Sunghyun Wee, Geunjae Choi, Hyeonjin Kim +2LLM QuantizationNeural Network Quantization

    Seoul National University · LG Electronics

  13. Task-Phase-Conditioned Expert Routing Is Not a Reliable Proxy for Quantization Sensitivity in MoE FFN Tensors

    Oct 14, 2026Yifan LiuQuantization Sensitivity AnalysisMixture-of-Experts Quantization

    UIUC MCS Student

  14. RoLaQ: Joint Rotation and Range Calibration for 2-Bit KV Caches in Multi-Head Latent Attention

    Oct 14, 2026Shiyu Ji, Peng Ling, Chen Lin +4KV-Cache QuantizationLow-Bit Quantization

    Research Center for Social Computing and Interactive Robotics, Harbin Institute of Technology, China · Tsinghua University, China · Baidu Inc., China

  15. Revise-TTS: A Non-Masking Refinement Framework for Masked Diffusion Models in Text-to-Speech

    Oct 14, 2026Wanli Sun, Dan Su, Anton RagniTTS SynthesisZero-Shot TTS

    School of Computer Science, University of Sheffield, Sheffield, UK · HojoAI, Beijing, China

  16. Revisiting Error Feedback for Model Quantization

    Oct 13, 2026Wai-Yiu Keung, Chi Cui, Wing-Kin Ma +2Neural Network QuantizationLLM Quantization

    The Chinese University of Hong Kong, Hong Kong SAR of China · Universidad Carlos III de Madrid, Spain · Aarhus University, Denmark

  17. LocalTrain: Integer-Only Local Learning for Energy-Efficient CNN Training on Edge FPGAs

    Oct 12, 2026Shiqi Ding, Xuanyu Liang, Xinyang Liu +4On-Device TrainingEnergy-Efficient ML

    University of Cambridge · University College London · University of Bristol

  18. Memory-Efficient Integer-Only Training of Deep Neural Networks

    Oct 12, 2026Hazem Hesham Yousef Shalby, Fabrizio Pittorino, Manuel RoveriLow-Precision TrainingNeural Network Quantization

    Dipartimento di Elettronica, Informazione e Bioingegneria (DEIB), Politecnico di Milano, Milan, Italy

  19. Hardware-Friendly Token-Group Activation Quantization for Low-Bit Mamba Super-Resolution

    Oct 12, 2026Jinwoo Chung, Jangho KimActivation QuantizationPost-Training Quantization

    Kookmin University Seoul, Republic of Korea

  20. When Does Compensating Inherited Quantization Error Help? Mean-Square Guarantees for Layer-Wise Quantization and Their Limits

    Oct 12, 2026Tianhao GuoQuantization Error CompensationNeural Network Quantization

    College of Physics and Electronic Engineering, Shanxi University, Taiyuan 030006, China

  21. Preserving Updates in Low-Bit Recurrent State Quantization

    Oct 11, 2026Haotian Li, Liran Dong, Kaicheng Xiao +1Recurrent-State QuantizationLow-Bit Quantization

    The Chinese University of Hong Kong

  22. HGA-Quant: Heterogeneity-Aware Quantization for AutoRegressive Visual Generation Models

    Oct 11, 2026Xinmeng Liu, Xianglong Yan, Kaicheng Yang +2Post-Training QuantizationNeural Network Quantization

    Shanghai Jiao Tong University · Xi’an University of Electronic Science and Technology

  23. When Dynamic Scaling Fails: A Scale-State Feedback Governs Recurrent-State Quantization in Linear-Attention and SSM LLMs

    Oct 10, 2026Yuhang JiangRecurrent-State QuantizationLLM Quantization

    Independent Researcher

  24. 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

    Computer Engineering Department, Faculty of Engineering, Cairo University, Giza, Egypt

  25. FidelityQ: Preserving Predictive Fidelity in Ultra-Low-Bit Language Model Quantization

    Oct 10, 2026Yujie Chen, Weiyan Zheng, Yiwu Yao +7Low-Bit QuantizationNeural Network Quantization

    The Hong Kong Polytechnic University · Huawei Technologies Ltd. · The University of Hong Kong +2

  26. DualQuant: Dual-scale Calibration-free Weight-and-Activation Quantization for LLMs

    Oct 9, 2026Mahsa Salmani, Sayeh Sharify, Hesham MostafaLLM QuantizationPost-Training Quantization

    d-Matrix

  27. Rounding in Preconditioner Space: Redesigning 4-bit AdamW Optimizer-State Quantization

    Oct 8, 2026Hanyang Li, Shao Tang, Daniel Thomas Braithwaite +7Stochastic Rounding4-Bit Quantization

    University of California, Berkeley · Nubank

  28. Read What Matters: Query-Adaptive Quantization for KV Caches

    Oct 8, 2026Siddharth Bhandari, Lucas Gretta, Krishna Balasubramanian +1KV-Cache QuantizationKV-Cache Compression

    Amazon · University of California, Berkeley

  29. TR-PTQ: High-Accuracy Integer-Only Transformer Post Training Quantization via Taylor Region Reformulation

    Oct 7, 2026Eliyahu Levy, Adam Teman, Yoni PugachovPost-Training QuantizationNeural Network Quantization

    Faculty of Engineering, Bar-Ilan University, Ramat Gan, Israel

  30. Layerwise Error Attribution for Fast and Robust Mixed-Precision Post-Training Quantization

    Oct 7, 2026Samy Houache, Yann Traonmilin, Jean-François AujolPost-Training QuantizationNeural Network Quantization

    IMB, UB · UB, IMB