{"total":14,"rows":[{"id":"2205.07877","title":"A Comprehensive Survey on Model Quantization for Deep Neural Networks in Image Classification","created":"2022-05-14","cited_by_count":65,"area":null},{"id":"2206.04459","title":"SDQ: Stochastic Differentiable Quantization with Mixed Precision","created":"2022-06-09","cited_by_count":28,"area":null},{"id":"2205.11244","title":"A Silicon Photonic Accelerator for Convolutional Neural Networks with Heterogeneous Quantization","created":"2022-05-17","cited_by_count":9,"area":null},{"id":"2205.12918","title":"A Low Memory Footprint Quantized Neural Network for Depth Completion of Very Sparse Time-of-Flight Depth Maps","created":"2022-05-25","cited_by_count":6,"area":null},{"id":"2301.13330","title":"Efficient and Effective Methods for Mixed Precision Neural Network Quantization for Faster, Energy-efficient Inference","created":"2023-01-30","cited_by_count":3,"area":null},{"id":"2307.02894","title":"Free Bits: Latency Optimization of Mixed-Precision Quantized Neural Networks on the Edge","created":"2023-07-06","cited_by_count":3,"area":null},{"id":"2606.19558","title":"Displacement Is Not Direction: Evaluating Fidelity Metrics for Quantized LLM Deployment","created":"2026-06-17","cited_by_count":3,"area":null},{"id":"2304.06987","title":"Unsupervised ANN-Based Equalizer and Its Trainable FPGA Implementation","created":"2023-04-14","cited_by_count":2,"area":null},{"id":"2103.13322","title":"DNN Quantization with Attention","created":"2021-03-24","cited_by_count":1,"area":null},{"id":"2204.13666","title":"Schr\\\"odinger's FP: Dynamic Adaptation of Floating-Point Containers for Deep Learning Training","created":"2022-04-28","cited_by_count":1,"area":null},{"id":"2404.16876","title":"AdaQAT: Adaptive Bit-Width Quantization-Aware Training","created":"2024-04-22","cited_by_count":1,"area":null},{"id":"2405.02323","title":"CNN-Based Equalization for Communications: Achieving Gigabit Throughput with a Flexible FPGA Hardware Architecture","created":"2024-04-22","cited_by_count":1,"area":null},{"id":"2201.08830","title":"APack: Off-Chip, Lossless Data Compression for Efficient Deep Learning Inference","created":"2022-01-21","cited_by_count":0,"area":null},{"id":"2211.06982","title":"FullPack: Full Vector Utilization for Sub-Byte Quantized Inference on General Purpose CPUs","created":"2022-11-13","cited_by_count":0,"area":null}],"next_cursor":null}