{"total":16,"rows":[{"id":"2109.15082","title":"Towards Efficient Post-training Quantization of Pre-trained Language Models","created":"2021-09-30","cited_by_count":39,"area":null},{"id":"2102.08329","title":"An Information-Theoretic Justification for Model Pruning","created":"2021-02-16","cited_by_count":25,"area":null},{"id":"2310.11028","title":"Matrix Compression via Randomized Low Rank and Low Precision Factorization","created":"2023-10-17","cited_by_count":25,"area":null},{"id":"2312.09028","title":"Design Space Exploration of Low-Bit Quantized Neural Networks for Visual Place Recognition","created":"2023-12-14","cited_by_count":11,"area":null},{"id":"2102.07725","title":"Neural Network Compression for Noisy Storage Devices","created":"2021-02-15","cited_by_count":8,"area":null},{"id":"2204.02965","title":"LilNetX: Lightweight Networks with EXtreme Model Compression and Structured Sparsification","created":"2022-04-06","cited_by_count":7,"area":null},{"id":"2505.03031","title":"Radio: Rate-Distortion Optimization for Large Language Model Compression","created":"2025-05-05","cited_by_count":5,"area":null},{"id":"2112.05053","title":"Illumination and Temperature-Aware Multispectral Networks for Edge-Computing-Enabled Pedestrian Detection","created":"2021-12-09","cited_by_count":3,"area":null},{"id":"2405.06038","title":"From Algorithm to Hardware: A Survey on Efficient and Safe Deployment of Deep Neural Networks","created":"2024-05-09","cited_by_count":2,"area":null},{"id":"2409.02026","title":"Foundations of Large Language Model Compression -- Part 1: Weight Quantization","created":"2024-09-03","cited_by_count":2,"area":null},{"id":"2202.11277","title":"Minimax Optimal Quantization of Linear Models: Information-Theoretic Limits and Efficient Algorithms","created":"2022-02-23","cited_by_count":1,"area":null},{"id":"2309.02855","title":"Bandwidth-efficient Inference for Neural Image Compression","created":"2023-09-06","cited_by_count":1,"area":null},{"id":"2212.09358","title":"A Soft SIMD Based Energy Efficient Computing Microarchitecture","created":"2022-12-19","cited_by_count":0,"area":null},{"id":"2503.00796","title":"An Efficient 3D Convolutional Neural Network with Channel-wise, Spatial-grouped, and Temporal Convolutions","created":"2025-03-02","cited_by_count":0,"area":null},{"id":"2508.16863","title":"Delta-SVD: Efficient Compression for Personalized Text-to-Image Models","created":"2025-08-23","cited_by_count":0,"area":null},{"id":"2509.01592","title":"Securing Radiation Detection Systems with an Efficient TinyML-Based IDS for Edge Devices","created":"2025-09-01","cited_by_count":0,"area":null}],"next_cursor":null}