{"total":143,"rows":[{"id":"2101.09671","title":"Pruning and Quantization for Deep Neural Network Acceleration: A Survey","created":"2021-01-24","cited_by_count":263,"area":null},{"id":"2210.08277","title":"Deep Differentiable Logic Gate Networks","created":"2022-10-15","cited_by_count":67,"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":"2101.05108","title":"Fast convolutional neural networks on FPGAs with hls4ml","created":"2021-01-13","cited_by_count":42,"area":null},{"id":"2411.04732","title":"Convolutional Differentiable Logic Gate Networks","created":"2024-11-07","cited_by_count":37,"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":"2204.11786","title":"Enable Deep Learning on Mobile Devices: Methods, Systems, and Applications","created":"2022-04-25","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":"2309.02334","title":"PolyLUT: Learning Piecewise Polynomials for Ultra-Low Latency FPGA LUT-based Inference","created":"2023-09-05","cited_by_count":30,"area":null},{"id":"2305.05750","title":"A Systematic Literature Review on Hardware Reliability Assessment Methods for Deep Neural Networks","created":"2023-05-09","cited_by_count":23,"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":"2403.00849","title":"NeuraLUT: Hiding Neural Network Density in Boolean Synthesizable Functions","created":"2024-02-29","cited_by_count":21,"area":null},{"id":"2102.11646","title":"HardCoRe-NAS: Hard Constrained diffeRentiable Neural Architecture Search","created":"2021-02-23","cited_by_count":20,"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":"2104.08215","title":"\"BNN - BN = ?\": Training Binary Neural Networks without Batch Normalization","created":"2021-04-16","cited_by_count":17,"area":null},{"id":"2107.05530","title":"ROBIN: A Robust Optical Binary Neural Network Accelerator","created":"2021-07-12","cited_by_count":15,"area":null},{"id":"2504.00592","title":"NeuraLUT-Assemble: Hardware-aware Assembling of Sub-Neural Networks for Efficient LUT Inference","created":"2025-04-01","cited_by_count":14,"area":null},{"id":"2512.12850","title":"KANEL\\'E: Kolmogorov-Arnold Networks for Efficient LUT-based Evaluation","created":"2025-12-14","cited_by_count":13,"area":null},{"id":"2110.00478","title":"SECDA: Efficient Hardware/Software Co-Design of FPGA-based DNN Accelerators for Edge Inference","created":"2021-10-01","cited_by_count":12,"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":"2308.13504","title":"A2Q: Accumulator-Aware Quantization with Guaranteed Overflow Avoidance","created":"2023-08-25","cited_by_count":12,"area":null},{"id":"2406.04910","title":"PolyLUT-Add: FPGA-based LUT Inference with Wide Inputs","created":"2024-06-07","cited_by_count":12,"area":null},{"id":"2102.04270","title":"Enabling Binary Neural Network Training on the Edge","created":"2021-02-08","cited_by_count":11,"area":null},{"id":"2201.01863","title":"CFU Playground: Full-Stack Open-Source Framework for Tiny Machine Learning (tinyML) Acceleration on FPGAs","created":"2022-01-05","cited_by_count":11,"area":null},{"id":"2203.04894","title":"A Brain-Inspired Low-Dimensional Computing Classifier for Inference on Tiny Devices","created":"2022-03-09","cited_by_count":11,"area":null},{"id":"2303.08226","title":"DeepAxe: A Framework for Exploration of Approximation and Reliability Trade-offs in DNN Accelerators","created":"2023-03-14","cited_by_count":11,"area":null},{"id":"2206.07527","title":"QONNX: Representing Arbitrary-Precision Quantized Neural Networks","created":"2022-06-15","cited_by_count":10,"area":null},{"id":"2407.04168","title":"Learning Interpretable Differentiable Logic Networks","created":"2024-07-04","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":"2401.09509","title":"Exploration of Activation Fault Reliability in Quantized Systolic Array-Based DNN Accelerators","created":"2024-01-17","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":"2304.10618","title":"ULEEN: A Novel Architecture for Ultra Low-Energy Edge Neural Networks","created":"2023-04-20","cited_by_count":8,"area":null},{"id":"2501.08043","title":"PolyLUT: Ultra-low Latency Polynomial Inference with Hardware-Aware Structured Pruning","created":"2025-01-14","cited_by_count":8,"area":null},{"id":"2102.03456","title":"BinaryCoP: Binary Neural Network-based COVID-19 Face-Mask Wear and Positioning Predictor on Edge Devices","created":"2021-02-06","cited_by_count":7,"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":"2303.17218","title":"HARFLOW3D: A Latency-Oriented 3D-CNN Accelerator Toolflow for HAR on FPGA Devices","created":"2023-03-30","cited_by_count":5,"area":null},{"id":"2312.00454","title":"An Encoding Framework for Binarized Images using HyperDimensional Computing","created":"2023-12-01","cited_by_count":5,"area":null},{"id":"2404.07164","title":"PIM-Opt: Demystifying Distributed Optimization Algorithms on a Real-World Processing-In-Memory System","created":"2024-04-10","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":"2301.04954","title":"Reaching the Edge of the Edge: Image Analysis in Space","created":"2023-01-12","cited_by_count":4,"area":null},{"id":"2305.05187","title":"DeepFire2: A Convolutional Spiking Neural Network Accelerator on FPGAs","created":"2023-05-09","cited_by_count":4,"area":null},{"id":"2308.01193","title":"Mercury: An Automated Remote Side-channel Attack to Nvidia Deep Learning Accelerator","created":"2023-08-02","cited_by_count":4,"area":null},{"id":"2309.16733","title":"Resilience of Deep Learning applications: a systematic literature review of analysis and hardening techniques","created":"2023-09-27","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":"2502.05850","title":"MetaML-Pro: Cross-Stage Design Flow Automation for Efficient Deep Learning Acceleration","created":"2025-02-09","cited_by_count":4,"area":null},{"id":"2104.10044","title":"BCNN: Binary Complex Neural Network","created":"2021-03-28","cited_by_count":3,"area":null},{"id":"2105.06250","title":"3U-EdgeAI: Ultra-Low Memory Training, Ultra-Low BitwidthQuantization, and Ultra-Low Latency Acceleration","created":"2021-05-11","cited_by_count":3,"area":null},{"id":"2112.02346","title":"Logic Shrinkage: Learned FPGA Netlist Sparsity for Efficient Neural Network Inference","created":"2021-12-04","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":"2302.09221","title":"Moby: Empowering 2D Models for Efficient Point Cloud Analytics on the Edge","created":"2023-02-18","cited_by_count":3,"area":null},{"id":"2304.08400","title":"ATHEENA: A Toolflow for Hardware Early-Exit Network Automation","created":"2023-04-17","cited_by_count":3,"area":null},{"id":"2306.08746","title":"MetaML: Automating Customizable Cross-Stage Design-Flow for Deep Learning Acceleration","created":"2023-06-14","cited_by_count":3,"area":null},{"id":"2307.01056","title":"A 3 TOPS/W RISC-V Parallel Cluster for Inference of Fine-Grain Mixed-Precision Quantized Neural Networks","created":"2023-07-03","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":"2408.09209","title":"H2PIPE: High throughput CNN Inference on FPGAs with High-Bandwidth Memory","created":"2024-08-17","cited_by_count":3,"area":null},{"id":"2409.05905","title":"Towards Narrowing the Generalization Gap in Deep Boolean Networks","created":"2024-09-06","cited_by_count":3,"area":null},{"id":"2508.21524","title":"Binary Weight Multi-Bit Activation Quantization for Compute-in-Memory CNN Accelerators","created":"2025-08-29","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":"2104.00210","title":"Training Multi-bit Quantized and Binarized Networks with A Learnable Symmetric Quantizer","created":"2021-04-01","cited_by_count":2,"area":null},{"id":"2106.14771","title":"HALF: Holistic Auto Machine Learning for FPGAs","created":"2021-06-28","cited_by_count":2,"area":null},{"id":"2106.15021","title":"How to Reach Real-Time AI on Consumer Devices? Solutions for Programmable and Custom Architectures","created":"2021-06-21","cited_by_count":2,"area":null},{"id":"2202.04271","title":"Adversarial Detection without Model Information","created":"2022-02-09","cited_by_count":2,"area":null},{"id":"2208.01944","title":"PalQuant: Accelerating High-precision Networks on Low-precision Accelerators","created":"2022-08-03","cited_by_count":2,"area":null},{"id":"2302.05996","title":"Quark: An Integer RISC-V Vector Processor for Sub-Byte Quantized DNN Inference","created":"2023-02-12","cited_by_count":2,"area":null},{"id":"2303.02284","title":"Fixed-point quantization aware training for on-device keyword-spotting","created":"2023-03-04","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":"2403.08980","title":"Architectural Implications of Neural Network Inference for High Data-Rate, Low-Latency Scientific Applications","created":"2024-03-13","cited_by_count":2,"area":null},{"id":"2407.08272","title":"PowerYOLO: Mixed Precision Model for Hardware Efficient Object Detection with Event Data","created":"2024-07-11","cited_by_count":2,"area":null},{"id":"2408.15561","title":"CGRA4ML: A Hardware/Software Framework to Implement Neural Networks for Scientific Edge Computing","created":"2024-08-28","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":"2504.19797","title":"Dynamic Tsetlin Machine Accelerators for On-Chip Training at the Edge using FPGAs","created":"2025-04-28","cited_by_count":2,"area":null},{"id":"2505.23615","title":"Learning Interpretable Differentiable Logic Networks for Tabular Regression","created":"2025-05-29","cited_by_count":2,"area":null},{"id":"2506.03938","title":"FPGA-Enabled Machine Learning Applications in Earth Observation: A Systematic Review","created":"2025-06-04","cited_by_count":2,"area":null},{"id":"2104.01699","title":"A Configurable BNN ASIC using a Network of Programmable Threshold Logic Standard Cells","created":"2021-04-04","cited_by_count":1,"area":null},{"id":"2110.05403","title":"Machine Learning for the Control and Monitoring of Electric Machine Drives: Advances and Trends","created":"2021-10-11","cited_by_count":1,"area":null},{"id":"2202.03716","title":"Binary Neural Networks as a general-propose compute paradigm for on-device computer vision","created":"2022-02-08","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":"2306.13515","title":"Binary domain generalization for sparsifying binary neural networks","created":"2023-06-23","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":"2311.14005","title":"When Side-Channel Attacks Break the Black-Box Property of Embedded Artificial Intelligence","created":"2023-11-23","cited_by_count":1,"area":null},{"id":"2401.10689","title":"A Lightweight Multi-Attack CAN Intrusion Detection System on Hybrid FPGAs","created":"2024-01-19","cited_by_count":1,"area":null},{"id":"2401.11030","title":"Exploring Highly Quantised Neural Networks for Intrusion Detection in Automotive CAN","created":"2024-01-19","cited_by_count":1,"area":null},{"id":"2501.18953","title":"StruM: Structured Mixed Precision for Efficient Deep Learning Hardware Codesign","created":"2025-01-31","cited_by_count":1,"area":null},{"id":"2502.12173","title":"nanoML for Human Activity Recognition","created":"2025-02-13","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":"2601.19940","title":"Continuous-Flow Data-Rate-Aware CNN Inference on FPGA","created":"2026-01-16","cited_by_count":1,"area":null},{"id":"2602.05830","title":"Learning Compact Boolean Networks","created":"2026-02-05","cited_by_count":1,"area":null},{"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":"2607.08427","title":"FPGN: Redefining Ultra-Fast Programmable Gate-based Neural Acceleration with Differentiable LUTs","created":"2026-07-09","cited_by_count":1,"area":null},{"id":"2101.00793","title":"A Framework for Fast Scalable BNN Inference using Googlenet and Transfer Learning","created":"2021-01-04","cited_by_count":0,"area":null},{"id":"2101.09492","title":"MinConvNets: A new class of multiplication-less Neural Networks","created":"2021-01-23","cited_by_count":0,"area":null},{"id":"2102.01351","title":"Hardware-efficient Residual Networks for FPGAs","created":"2021-02-02","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":"2201.06878","title":"Hardware-Efficient Deconvolution-Based GAN for Edge Computing","created":"2022-01-18","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}],"next_cursor":"100"}