{"total":56,"rows":[{"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":"2110.06804","title":"A comprehensive review of Binary Neural Network","created":"2021-10-11","cited_by_count":45,"area":null},{"id":"2101.05108","title":"Fast convolutional neural networks on FPGAs with hls4ml","created":"2021-01-13","cited_by_count":42,"area":null},{"id":"2312.15159","title":"Understanding the Potential of FPGA-Based Spatial Acceleration for Large Language Model Inference","created":"2023-12-23","cited_by_count":33,"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":"2102.11289","title":"Ps and Qs: Quantization-aware pruning for efficient low latency neural network inference","created":"2021-02-22","cited_by_count":31,"area":null},{"id":"2312.14190","title":"Machine Learning for Anomaly Detection in Particle Physics","created":"2023-12-20","cited_by_count":30,"area":null},{"id":"2503.02891","title":"Vision Transformers on the Edge: A Comprehensive Survey of Model Compression and Acceleration Strategies","created":"2025-02-26","cited_by_count":24,"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":"2203.12852","title":"Graph Neural Networks in Particle Physics: Implementations, Innovations, and Challenges","created":"2022-03-23","cited_by_count":12,"area":null},{"id":"2209.14065","title":"LL-GNN: Low Latency Graph Neural Networks on FPGAs for High Energy Physics","created":"2022-09-28","cited_by_count":12,"area":null},{"id":"2308.13504","title":"A2Q: Accumulator-Aware Quantization with Guaranteed Overflow Avoidance","created":"2023-08-25","cited_by_count":12,"area":null},{"id":"2206.07527","title":"QONNX: Representing Arbitrary-Precision Quantized Neural Networks","created":"2022-06-15","cited_by_count":10,"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":"2405.00645","title":"HGQ: High Granularity Quantization for Real-time Neural Networks on FPGAs","created":"2024-05-01","cited_by_count":9,"area":null},{"id":"2512.01463","title":"hls4ml: A Flexible, Open-Source Platform for Deep Learning Acceleration on Reconfigurable Hardware","created":"2025-12-01","cited_by_count":9,"area":null},{"id":"2403.03322","title":"Deep Configuration Performance Learning: A Systematic Survey and Taxonomy","created":"2024-03-05","cited_by_count":8,"area":null},{"id":"2308.05170","title":"FPGA Resource-aware Structured Pruning for Real-Time Neural Networks","created":"2023-08-09","cited_by_count":7,"area":null},{"id":"2301.00290","title":"BARVINN: Arbitrary Precision DNN Accelerator Controlled by a RISC-V CPU","created":"2022-12-31","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":"2409.09044","title":"ElasticAI: Creating and Deploying Energy-Efficient Deep Learning Accelerator for Pervasive Computing","created":"2024-08-29","cited_by_count":5,"area":null},{"id":"2103.05600","title":"unzipFPGA: Enhancing FPGA-based CNN Engines with On-the-Fly Weights Generation","created":"2021-03-09","cited_by_count":4,"area":null},{"id":"2309.01587","title":"SATAY: A Streaming Architecture Toolflow for Accelerating YOLO Models on FPGA Devices","created":"2023-09-04","cited_by_count":4,"area":null},{"id":"2311.12359","title":"Shedding the Bits: Pushing the Boundaries of Quantization with Minifloats on FPGAs","created":"2023-11-21","cited_by_count":4,"area":null},{"id":"2407.03852","title":"Low-latency machine learning FPGA accelerator for multi-qubit-state discrimination","created":"2024-07-04","cited_by_count":4,"area":null},{"id":"2205.08243","title":"IIsy: Practical In-Network Classification","created":"2022-05-17","cited_by_count":3,"area":null},{"id":"2208.04854","title":"Design of High-Throughput Mixed-Precision CNN Accelerators on FPGA","created":"2022-08-09","cited_by_count":3,"area":null},{"id":"2301.13376","title":"Quantized Neural Networks for Low-Precision Accumulation with Guaranteed Overflow Avoidance","created":"2023-01-31","cited_by_count":3,"area":null},{"id":"2403.10538","title":"MATADOR: Automated System-on-Chip Tsetlin Machine Design Generation for Edge Applications","created":"2024-03-03","cited_by_count":3,"area":null},{"id":"2511.00812","title":"LL-ViT: Edge Deployable Vision Transformers with Look Up Table Neurons","created":"2025-11-02","cited_by_count":3,"area":null},{"id":"2102.01341","title":"Benchmarking Quantized Neural Networks on FPGAs with FINN","created":"2021-02-02","cited_by_count":2,"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":"2304.12474","title":"Design optimization for high-performance computing using FPGA","created":"2023-04-24","cited_by_count":2,"area":null},{"id":"2407.06170","title":"Real-Time Spacecraft Pose Estimation Using Mixed-Precision Quantized Neural Network on COTS Reconfigurable MPSoC","created":"2024-06-06","cited_by_count":2,"area":null},{"id":"2411.11852","title":"LUTMUL: Exceed Conventional FPGA Roofline Limit by LUT-based Efficient Multiplication for Neural Network Inference","created":"2024-11-01","cited_by_count":2,"area":null},{"id":"2602.16336","title":"HAWX: A Hardware-Aware FrameWork for Fast and Scalable ApproXimation of DNNs","created":"2026-02-18","cited_by_count":2,"area":null},{"id":"2203.11081","title":"Image Classification on Accelerated Neural Networks","created":"2022-03-21","cited_by_count":1,"area":null},{"id":"2207.10482","title":"LPYOLO: Low Precision YOLO for Face Detection on FPGA","created":"2022-07-21","cited_by_count":1,"area":null},{"id":"2301.06193","title":"RedBit: An End-to-End Flexible Framework for Evaluating the Accuracy of Quantized CNNs","created":"2023-01-15","cited_by_count":1,"area":null},{"id":"2303.00031","title":"Tiny Classifier Circuits: Evolving Accelerators for Tabular Data","created":"2023-02-28","cited_by_count":1,"area":null},{"id":"2305.05388","title":"VEDLIoT -- Next generation accelerated AIoT systems and applications","created":"2023-05-09","cited_by_count":1,"area":null},{"id":"2307.13412","title":"Mitigating Memory Wall Effects in CNN Engines with On-the-Fly Weights Generation","created":"2023-07-25","cited_by_count":1,"area":null},{"id":"2408.07404","title":"Efficient Edge AI: Deploying Convolutional Neural Networks on FPGA with the Gemmini Accelerator","created":"2024-08-14","cited_by_count":1,"area":null},{"id":"2508.10370","title":"eMamba: Efficient Acceleration Framework for Mamba Models in Edge Computing","created":"2025-08-14","cited_by_count":1,"area":"ssm"},{"id":"2602.23455","title":"BiKA: Kolmogorov-Arnold-Network-inspired Ultra Lightweight Neural Network Hardware Accelerator","created":"2026-02-26","cited_by_count":1,"area":null},{"id":"2103.14007","title":"Enabling Incremental Training with Forward Pass for Edge Devices","created":"2021-03-25","cited_by_count":0,"area":null},{"id":"2104.02303","title":"Exploration of Hardware Acceleration Methods for an XNOR Traffic Signs Classifier","created":"2021-04-06","cited_by_count":0,"area":null},{"id":"2205.10653","title":"Towards real-time and energy efficient Siamese tracking -- a hardware-software approach","created":"2022-05-21","cited_by_count":0,"area":null},{"id":"2308.13735","title":"MST-compression: Compressing and Accelerating Binary Neural Networks with Minimum Spanning Tree","created":"2023-08-26","cited_by_count":0,"area":null},{"id":"2401.03534","title":"Physics-informed Neural Networks for Encoding Dynamics in Real Physical Systems","created":"2024-01-07","cited_by_count":0,"area":null},{"id":"2403.01845","title":"NASH: Neural Architecture Search for Hardware-Optimized Machine Learning Models","created":"2024-03-04","cited_by_count":0,"area":null},{"id":"2506.20810","title":"FINN-GL: Generalized Mixed-Precision Extensions for FPGA-Accelerated LSTMs","created":"2025-06-25","cited_by_count":0,"area":null},{"id":"2507.07903","title":"Hardware-Aware Feature Extraction Quantisation for Real-Time Visual Odometry on FPGA Platforms","created":"2025-07-10","cited_by_count":0,"area":null},{"id":"2508.21493","title":"SIRA: Scaled-Integer Range Analysis for Optimizing FPGA Dataflow Neural Network Accelerators","created":"2025-08-29","cited_by_count":0,"area":null},{"id":"2602.23334","title":"Bitwise Systolic Array Architecture for Runtime-Reconfigurable Multi-precision Quantized Multiplication on Hardware Accelerators","created":"2026-02-26","cited_by_count":0,"area":null}],"next_cursor":null}