{"total":25,"rows":[{"id":"2208.07339","title":"LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale","created":"2022-08-15","cited_by_count":906,"area":null},{"id":"2212.09720","title":"The case for 4-bit precision: k-bit Inference Scaling Laws","created":"2022-12-19","cited_by_count":251,"area":null},{"id":"2212.08059","title":"Rethinking Vision Transformers for MobileNet Size and Speed","created":"2022-12-15","cited_by_count":121,"area":null},{"id":"2304.09145","title":"Outlier Suppression+: Accurate quantization of large language models by equivalent and optimal shifting and scaling","created":"2023-04-18","cited_by_count":61,"area":null},{"id":"2306.15552","title":"A Survey on Deep Learning Hardware Accelerators for Heterogeneous HPC Platforms","created":"2023-06-27","cited_by_count":21,"area":null},{"id":"2311.05161","title":"Enhancing Computation Efficiency in Large Language Models through Weight and Activation Quantization","created":"2023-11-09","cited_by_count":20,"area":null},{"id":"2207.09455","title":"To update or not to update? Neurons at equilibrium in deep models","created":"2022-07-19","cited_by_count":13,"area":null},{"id":"2207.08822","title":"Is Integer Arithmetic Enough for Deep Learning Training?","created":"2022-07-18","cited_by_count":12,"area":null},{"id":"2505.05530","title":"Low-bit Model Quantization for Deep Neural Networks: A Survey","created":"2025-05-08","cited_by_count":11,"area":null},{"id":"2409.01990","title":"Designing Large Foundation Models for Efficient Training and Inference: A Survey","created":"2024-09-03","cited_by_count":7,"area":null},{"id":"2508.15008","title":"Neural Network Quantization for Microcontrollers: A Comprehensive Survey of Methods, Platforms, and Applications","created":"2025-08-20","cited_by_count":7,"area":null},{"id":"2504.06748","title":"Efficient Deployment of Spiking Neural Networks on SpiNNaker2 for DVS Gesture Recognition Using Neuromorphic Intermediate Representation","created":"2025-04-09","cited_by_count":6,"area":null},{"id":"2311.02758","title":"M4BRAM: Mixed-Precision Matrix-Matrix Multiplication in FPGA Block RAMs","created":"2023-11-05","cited_by_count":5,"area":null},{"id":"2411.05873","title":"Poor Man's Training on MCUs: A Memory-Efficient Quantized Back-Propagation-Free Approach","created":"2024-11-07","cited_by_count":5,"area":null},{"id":"2403.00176","title":"SoD$^2$: Statically Optimizing Dynamic Deep Neural Network","created":"2024-02-29","cited_by_count":4,"area":null},{"id":"2409.00297","title":"On Expressive Power of Quantized Neural Networks under Fixed-Point Arithmetic","created":"2024-08-30","cited_by_count":4,"area":null},{"id":"2405.16339","title":"BOLD: Boolean Logic Deep Learning","created":"2024-05-25","cited_by_count":3,"area":null},{"id":"2311.07427","title":"Boolean Variation and Boolean Logic BackPropagation","created":"2023-11-13","cited_by_count":2,"area":null},{"id":"2407.18267","title":"MCU-MixQ: A HW/SW Co-optimized Mixed-precision Neural Network Design Framework for MCUs","created":"2024-07-17","cited_by_count":2,"area":null},{"id":"2302.14458","title":"Ultra-low Precision Multiplication-free Training for Deep Neural Networks","created":"2023-02-28","cited_by_count":1,"area":null},{"id":"2505.13461","title":"FPGA-based Acceleration for Convolutional Neural Networks: A Comprehensive Review","created":"2025-05-04","cited_by_count":1,"area":null},{"id":"2508.17069","title":"Optimizing Neural Networks with Learnable Non-Linear Activation Functions via Lookup-Based FPGA Acceleration","created":"2025-08-23","cited_by_count":1,"area":null},{"id":"2311.05317","title":"RepQ: Generalizing Quantization-Aware Training for Re-Parametrized Architectures","created":"2023-11-09","cited_by_count":0,"area":null},{"id":"2407.11037","title":"ISQuant: apply squant to the real deployment","created":"2024-07-05","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}