{"total":81,"rows":[{"id":"2101.09671","title":"Pruning and Quantization for Deep Neural Network Acceleration: A Survey","created":"2021-01-24","cited_by_count":263,"area":null},{"id":"2109.12948","title":"Understanding and Overcoming the Challenges of Efficient Transformer Quantization","created":"2021-09-27","cited_by_count":141,"area":null},{"id":"2206.09557","title":"LUT-GEMM: Quantized Matrix Multiplication based on LUTs for Efficient Inference in Large-Scale Generative Language Models","created":"2022-06-20","cited_by_count":105,"area":null},{"id":"2306.11987","title":"Training Transformers with 4-bit Integers","created":"2023-06-21","cited_by_count":60,"area":null},{"id":"2111.05193","title":"A Survey on Green Deep Learning","created":"2021-11-08","cited_by_count":52,"area":null},{"id":"2104.09987","title":"Differentiable Model Compression via Pseudo Quantization Noise","created":"2021-04-20","cited_by_count":45,"area":null},{"id":"2206.11357","title":"GACT: Activation Compressed Training for Generic Network Architectures","created":"2022-06-22","cited_by_count":31,"area":null},{"id":"2102.04782","title":"Distribution Adaptive INT8 Quantization for Training CNNs","created":"2021-02-09","cited_by_count":28,"area":null},{"id":"2502.12913","title":"GSQ-Tuning: Group-Shared Exponents Integer in Fully Quantized Training for LLMs On-Device Fine-tuning","created":"2025-02-18","cited_by_count":21,"area":null},{"id":"2211.01340","title":"POLICE: Provably Optimal Linear Constraint Enforcement for Deep Neural Networks","created":"2022-11-02","cited_by_count":19,"area":null},{"id":"2302.04453","title":"Data Quality-aware Mixed-precision Quantization via Hybrid Reinforcement Learning","created":"2023-02-09","cited_by_count":17,"area":null},{"id":"2206.09909","title":"Low-Precision Stochastic Gradient Langevin Dynamics","created":"2022-06-20","cited_by_count":12,"area":null},{"id":"2102.04270","title":"Enabling Binary Neural Network Training on the Edge","created":"2021-02-08","cited_by_count":11,"area":null},{"id":"2202.11453","title":"Bitwidth Heterogeneous Federated Learning with Progressive Weight Dequantization","created":"2022-02-23","cited_by_count":11,"area":null},{"id":"2311.18129","title":"Mixed-Precision Quantization for Federated Learning on Resource-Constrained Heterogeneous Devices","created":"2023-11-29","cited_by_count":11,"area":null},{"id":"2505.01043","title":"Low-Precision Training of Large Language Models: Methods, Challenges, and Opportunities","created":"2025-05-02","cited_by_count":11,"area":null},{"id":"2405.03637","title":"Collage: Light-Weight Low-Precision Strategy for LLM Training","created":"2024-05-06","cited_by_count":10,"area":null},{"id":"2112.15131","title":"Resource-Efficient Deep Learning: A Survey on Model-, Arithmetic-, and Implementation-Level Techniques","created":"2021-12-30","cited_by_count":9,"area":null},{"id":"2112.15139","title":"Finding the Task-Optimal Low-Bit Sub-Distribution in Deep Neural Networks","created":"2021-12-30","cited_by_count":9,"area":null},{"id":"2310.05079","title":"Revisiting Block-based Quantisation: What is Important for Sub-8-bit LLM Inference?","created":"2023-10-08","cited_by_count":8,"area":null},{"id":"2607.04422","title":"Full-Stack FP4: Stable LLM Pretraining with Quantized Projections, Optimizers, and Attention","created":"2026-07-05","cited_by_count":8,"area":null},{"id":"2102.02147","title":"Fixed-point Quantization of Convolutional Neural Networks for Quantized Inference on Embedded Platforms","created":"2021-02-03","cited_by_count":7,"area":null},{"id":"2105.04246","title":"In-Hindsight Quantization Range Estimation for Quantized Training","created":"2021-05-10","cited_by_count":7,"area":null},{"id":"2106.13914","title":"LNS-Madam: Low-Precision Training in Logarithmic Number System using Multiplicative Weight Update","created":"2021-06-26","cited_by_count":7,"area":null},{"id":"2110.02065","title":"SDR: Efficient Neural Re-ranking using Succinct Document Representation","created":"2021-10-03","cited_by_count":7,"area":null},{"id":"2208.06064","title":"Mixed-Precision Neural Networks: A Survey","created":"2022-08-11","cited_by_count":7,"area":null},{"id":"2102.07444","title":"FAT: Learning Low-Bitwidth Parametric Representation via Frequency-Aware Transformation","created":"2021-02-15","cited_by_count":6,"area":null},{"id":"2203.14645","title":"REx: Data-Free Residual Quantization Error Expansion","created":"2022-03-28","cited_by_count":6,"area":null},{"id":"2212.03246","title":"MobileTL: On-device Transfer Learning with Inverted Residual Blocks","created":"2022-12-05","cited_by_count":6,"area":null},{"id":"2201.12861","title":"Neural-PIM: Efficient Processing-In-Memory with Neural Approximation of Peripherals","created":"2022-01-30","cited_by_count":5,"area":null},{"id":"2305.18513","title":"SlimFit: Memory-Efficient Fine-Tuning of Transformer-based Models Using Training Dynamics","created":"2023-05-29","cited_by_count":5,"area":null},{"id":"2401.10724","title":"Real-Time Zero-Day Intrusion Detection System for Automotive Controller Area Network on FPGAs","created":"2024-01-19","cited_by_count":5,"area":null},{"id":"2101.11748","title":"Rethinking Floating Point Overheads for Mixed Precision DNN Accelerators","created":"2021-01-27","cited_by_count":4,"area":null},{"id":"2105.13890","title":"Towards Efficient Full 8-bit Integer DNN Online Training on Resource-limited Devices without Batch Normalization","created":"2021-05-27","cited_by_count":4,"area":null},{"id":"2201.02863","title":"PocketNN: Integer-only Training and Inference of Neural Networks via Direct Feedback Alignment and Pocket Activations in Pure C++","created":"2022-01-08","cited_by_count":4,"area":null},{"id":"2302.07612","title":"Towards Optimal Compression: Joint Pruning and Quantization","created":"2023-02-15","cited_by_count":4,"area":null},{"id":"2112.10149","title":"Elastic-Link for Binarized Neural Network","created":"2021-12-19","cited_by_count":3,"area":null},{"id":"2207.08867","title":"MCTensor: A High-Precision Deep Learning Library with Multi-Component Floating-Point","created":"2022-07-18","cited_by_count":3,"area":null},{"id":"2406.14082","title":"FLoCoRA: Federated learning compression with low-rank adaptation","created":"2024-06-20","cited_by_count":3,"area":null},{"id":"2108.13055","title":"Efficient Visual Recognition with Deep Neural Networks: A Survey on Recent Advances and New Directions","created":"2021-08-30","cited_by_count":2,"area":null},{"id":"2209.15287","title":"Verifiable and Energy Efficient Medical Image Analysis with Quantised Self-attentive Deep Neural Networks","created":"2022-09-30","cited_by_count":2,"area":null},{"id":"2301.13464","title":"Training with Mixed-Precision Floating-Point Assignments","created":"2023-01-31","cited_by_count":2,"area":null},{"id":"2401.16136","title":"Neural Network Training on Encrypted Data with TFHE","created":"2024-01-29","cited_by_count":2,"area":null},{"id":"2405.13365","title":"Communication-Efficient Federated Learning via Clipped Uniform Quantization","created":"2024-05-22","cited_by_count":2,"area":null},{"id":"2409.11650","title":"Art and Science of Quantizing Large-Scale Models: A Comprehensive Overview","created":"2024-09-18","cited_by_count":2,"area":null},{"id":"2504.09405","title":"Tin-Tin: Towards Tiny Learning on Tiny Devices with Integer-based Neural Network Training","created":"2025-04-13","cited_by_count":2,"area":null},{"id":"2505.02314","title":"NeuroSim V1.5: Improved Software Backbone for Benchmarking Compute-in-Memory Accelerators with Device and Circuit-level Non-idealities","created":"2025-05-05","cited_by_count":2,"area":null},{"id":"2607.06922","title":"Latency-Constrained DNN Architecture Learning for Edge Systems using Zerorized Batch Normalization","created":"2026-07-08","cited_by_count":2,"area":null},{"id":"2103.14493","title":"RCT: Resource Constrained Training for Edge AI","created":"2021-03-26","cited_by_count":1,"area":null},{"id":"2112.14834","title":"Training Quantized Deep Neural Networks via Cooperative Coevolution","created":"2021-12-23","cited_by_count":1,"area":null},{"id":"2203.09082","title":"Confidence Dimension for Deep Learning based on Hoeffding Inequality and Relative Evaluation","created":"2022-03-17","cited_by_count":1,"area":null},{"id":"2207.11912","title":"Dive into Big Model Training","created":"2022-07-25","cited_by_count":1,"area":null},{"id":"2305.10947","title":"Revisiting 16-bit Neural Network Training: A Practical Approach for Resource-Limited Learning","created":"2023-05-18","cited_by_count":1,"area":null},{"id":"2310.16320","title":"Enhancing Low-Precision Sampling via Stochastic Gradient Hamiltonian Monte Carlo","created":"2023-10-25","cited_by_count":1,"area":null},{"id":"2401.10689","title":"A Lightweight Multi-Attack CAN Intrusion Detection System on Hybrid FPGAs","created":"2024-01-19","cited_by_count":1,"area":null},{"id":"2401.11030","title":"Exploring Highly Quantised Neural Networks for Intrusion Detection in Automotive CAN","created":"2024-01-19","cited_by_count":1,"area":null},{"id":"2403.07339","title":"IM-Unpack: Training and Inference with Arbitrarily Low Precision Integers","created":"2024-03-12","cited_by_count":1,"area":null},{"id":"2407.09093","title":"On Exact Bit-level Reversible Transformers Without Changing Architectures","created":"2024-07-12","cited_by_count":1,"area":null},{"id":"2511.00874","title":"Training with Fewer Bits: Unlocking Edge LLMs Training with Stochastic Rounding","created":"2025-11-02","cited_by_count":1,"area":null},{"id":"2601.07086","title":"XBTorch: A Unified Framework for Modeling and Co-Design of Crossbar-Based Deep Learning Accelerators","created":"2026-01-11","cited_by_count":1,"area":null},{"id":"2603.03830","title":"Large-Margin Hyperdimensional Computing: A Learning-Theoretical Perspective","created":"2026-03-04","cited_by_count":1,"area":null},{"id":"2106.10796","title":"CD-SGD: Distributed Stochastic Gradient Descent with Compression and Delay Compensation","created":"2021-06-21","cited_by_count":0,"area":null},{"id":"2111.07046","title":"Iterative Training: Finding Binary Weight Deep Neural Networks with Layer Binarization","created":"2021-11-13","cited_by_count":0,"area":null},{"id":"2301.12809","title":"The Hidden Power of Pure 16-bit Floating-Point Neural Networks","created":"2023-01-30","cited_by_count":0,"area":null},{"id":"2303.15464","title":"Mathematical Challenges in Deep Learning","created":"2023-03-24","cited_by_count":0,"area":null},{"id":"2306.17442","title":"Designing strong baselines for ternary neural network quantization through support and mass equalization","created":"2023-06-30","cited_by_count":0,"area":null},{"id":"2311.15806","title":"PIPE : Parallelized Inference Through Post-Training Quantization Ensembling of Residual Expansions","created":"2023-11-27","cited_by_count":0,"area":null},{"id":"2401.10674","title":"Deep Learning-based Embedded Intrusion Detection System for Automotive CAN","created":"2024-01-19","cited_by_count":0,"area":null},{"id":"2401.12234","title":"A Lightweight FPGA-based IDS-ECU Architecture for Automotive CAN","created":"2024-01-19","cited_by_count":0,"area":null},{"id":"2409.14838","title":"MICSim: A Modular Simulator for Mixed-signal Compute-in-Memory based AI Accelerator","created":"2024-09-23","cited_by_count":0,"area":null},{"id":"2502.07189","title":"Exploring Vision Neural Network Pruning via Screening Methodology","created":"2025-02-11","cited_by_count":0,"area":null},{"id":"2503.16860","title":"PRIOT: Pruning-Based Integer-Only Transfer Learning for Embedded Systems","created":"2025-03-21","cited_by_count":0,"area":null},{"id":"2510.08999","title":"SQS: Bayesian DNN Compression through Sparse Quantized Sub-distributions","created":"2025-10-10","cited_by_count":0,"area":null},{"id":"2510.17058","title":"Bitwidth-Specific Logarithmic Arithmetic for Future Hardware-Accelerated Training","created":"2025-10-20","cited_by_count":0,"area":null},{"id":"2512.16476","title":"Batch Normalization-Free Fully Integer Quantized Neural Networks via Progressive Tandem Learning","created":"2025-12-18","cited_by_count":0,"area":null},{"id":"2603.13931","title":"True 4-Bit Quantized Convolutional Neural Network Training on CPU: Achieving Full-Precision Parity","created":"2026-03-14","cited_by_count":0,"area":null},{"id":"2606.24180","title":"Deep Learning Approaches for 3D Medical Scene Completion: From Geometric Modeling to Generative Paradigms","created":"2026-06-23","cited_by_count":0,"area":null},{"id":"2608.29667","title":"A Target-Centric Survey of Quantization-Aware Training","created":"2026-08-30","cited_by_count":0,"area":null},{"id":"2610.07489","title":"Deep Defence on Wheels: A Dual Intrusion Detection System Architecture for Comprehensive In-Vehicle Network Security","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.10630","title":"Phase-HDC: Replacing Optimizer History with Gradient Thresholds in Discrete Phase Learning","created":"2026-10-07","cited_by_count":0,"area":null},{"id":"2610.16298","title":"Memory-Efficient Integer-Only Training of Deep Neural Networks","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}