{"total":30,"rows":[{"id":"2103.13630","title":"A Survey of Quantization Methods for Efficient Neural Network Inference","created":"2021-03-25","cited_by_count":815,"area":null},{"id":"2103.05579","title":"hls4ml: An Open-Source Codesign Workflow to Empower Scientific Low-Power Machine Learning Devices","created":"2021-03-09","cited_by_count":62,"area":null},{"id":"2110.13041","title":"Applications and Techniques for Fast Machine Learning in Science","created":"2021-10-25","cited_by_count":32,"area":null},{"id":"2103.16701","title":"Charged particle tracking via edge-classifying interaction networks","created":"2021-03-30","cited_by_count":19,"area":null},{"id":"2405.20935","title":"Effective Interplay between Sparsity and Quantization: From Theory to Practice","created":"2024-05-31","cited_by_count":19,"area":null},{"id":"2112.02048","title":"Graph Neural Networks for Charged Particle Tracking on FPGAs","created":"2021-12-03","cited_by_count":17,"area":null},{"id":"2112.06126","title":"Neural Network Quantization for Efficient Inference: A Survey","created":"2021-12-08","cited_by_count":14,"area":null},{"id":"2207.07958","title":"FastML Science Benchmarks: Accelerating Real-Time Scientific Edge Machine Learning","created":"2022-07-16","cited_by_count":12,"area":null},{"id":"2305.09042","title":"Adaptive Federated Pruning in Hierarchical Wireless Networks","created":"2023-05-15","cited_by_count":10,"area":null},{"id":"2104.03408","title":"Nanosecond machine learning event classification with boosted decision trees in FPGA for high energy physics","created":"2021-04-07","cited_by_count":9,"area":null},{"id":"2206.11791","title":"Open-source FPGA-ML codesign for the MLPerf Tiny Benchmark","created":"2022-06-23","cited_by_count":9,"area":null},{"id":"2305.04099","title":"Symbolic Regression on FPGAs for Fast Machine Learning Inference","created":"2023-05-06","cited_by_count":9,"area":null},{"id":"2208.12866","title":"Reducing Computational Complexity of Neural Networks in Optical Channel Equalization: From Concepts to Implementation","created":"2022-08-26","cited_by_count":7,"area":null},{"id":"2409.17092","title":"Accumulator-Aware Post-Training Quantization for Large Language Models","created":"2024-09-25","cited_by_count":6,"area":null},{"id":"2401.10432","title":"A2Q+: Improving Accumulator-Aware Weight Quantization","created":"2024-01-19","cited_by_count":5,"area":null},{"id":"2506.18927","title":"From Tiny Machine Learning to Tiny Deep Learning: A Survey","created":"2025-06-21","cited_by_count":5,"area":null},{"id":"2603.18426","title":"Prune-then-Quantize or Quantize-then-Prune? Understanding the Impact of Compression Order in Joint Model Compression","created":"2026-03-19","cited_by_count":3,"area":null},{"id":"2203.16255","title":"Physics Community Needs, Tools, and Resources for Machine Learning","created":"2022-03-30","cited_by_count":2,"area":null},{"id":"2304.06745","title":"End-to-end codesign of Hessian-aware quantized neural networks for FPGAs and ASICs","created":"2023-04-13","cited_by_count":2,"area":null},{"id":"2206.12191","title":"Computational Complexity Evaluation of Neural Network Applications in Signal Processing","created":"2022-06-24","cited_by_count":1,"area":null},{"id":"2411.00907","title":"On the Impact of White-box Deployment Strategies for Edge AI on Latency and Model Performance","created":"2024-11-01","cited_by_count":1,"area":null},{"id":"2504.03387","title":"BitHEP -- The Limits of Low-Precision ML in HEP","created":"2025-04-04","cited_by_count":1,"area":null},{"id":"2504.09064","title":"PQS (Prune, Quantize, and Sort): Low-Bitwidth Accumulation of Dot Products in Neural Network Computations","created":"2025-04-12","cited_by_count":1,"area":null},{"id":"2601.11433","title":"Inter-patient ECG Arrhythmia Classification with LGNs and LUTNs","created":"2026-01-16","cited_by_count":1,"area":null},{"id":"2406.16962","title":"MetaGreen: Meta-Learning Inspired Transformer Selection for Green Semantic Communication","created":"2024-06-22","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":"2407.14560","title":"Automated and Holistic Co-design of Neural Networks and ASICs for Enabling In-Pixel Intelligence","created":"2024-07-18","cited_by_count":0,"area":null},{"id":"2408.02685","title":"Artificial Neural Networks for Photonic Applications: From Algorithms to Implementation","created":"2024-08-02","cited_by_count":0,"area":null},{"id":"2501.04213","title":"UPAQ: A Framework for Real-Time and Energy-Efficient 3D Object Detection in Autonomous Vehicles","created":"2025-01-08","cited_by_count":0,"area":null},{"id":"2609.32854","title":"Logic Gate Networks and Lookup Table Networks as Lightweight Hardware Classifiers for Inter-patient ECG Arrhythmia Classification","created":"2026-09-26","cited_by_count":0,"area":null}],"next_cursor":null}