{"total":80,"rows":[{"id":"2101.05108","title":"Fast convolutional neural networks on FPGAs with hls4ml","created":"2021-01-13","cited_by_count":42,"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":"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":"2205.14550","title":"Machine Learning for Microcontroller-Class Hardware: A Review","created":"2022-05-29","cited_by_count":28,"area":null},{"id":"2211.00454","title":"PELICAN: Permutation Equivariant and Lorentz Invariant or Covariant Aggregator Network for Particle Physics","created":"2022-11-01","cited_by_count":26,"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":"2103.16701","title":"Charged particle tracking via edge-classifying interaction networks","created":"2021-03-30","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":"2111.06417","title":"Online-compatible Unsupervised Non-resonant Anomaly Detection","created":"2021-11-11","cited_by_count":15,"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":"2207.07958","title":"FastML Science Benchmarks: Accelerating Real-Time Scientific Edge Machine Learning","created":"2022-07-16","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":"2402.01876","title":"Ultrafast jet classification on FPGAs for the HL-LHC","created":"2024-02-02","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":"2205.07690","title":"Real-time semantic segmentation on FPGAs for autonomous vehicles with hls4ml","created":"2022-05-16","cited_by_count":11,"area":null},{"id":"2210.08502","title":"FIT: A Metric for Model Sensitivity","created":"2022-10-16","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":"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":"2305.04099","title":"Symbolic Regression on FPGAs for Fast Machine Learning Inference","created":"2023-05-06","cited_by_count":9,"area":null},{"id":"2402.18593","title":"Sustainable Supercomputing for AI: GPU Power Capping at HPC Scale","created":"2024-02-25","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":"2304.07543","title":"Within-Camera Multilayer Perceptron DVS Denoising","created":"2023-04-15","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":"2501.14663","title":"End-to-end workflow for machine learning-based qubit readout with QICK and hls4ml","created":"2025-01-24","cited_by_count":8,"area":null},{"id":"2507.04535","title":"da4ml: Distributed Arithmetic for Real-time Neural Networks on FPGAs","created":"2025-07-06","cited_by_count":8,"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":"2308.05170","title":"FPGA Resource-aware Structured Pruning for Real-Time Neural Networks","created":"2023-08-09","cited_by_count":7,"area":null},{"id":"2401.09949","title":"SymbolNet: Neural Symbolic Regression with Adaptive Dynamic Pruning for Compression","created":"2024-01-18","cited_by_count":7,"area":null},{"id":"2411.19506","title":"Real-time Anomaly Detection at the L1 Trigger of CMS Experiment","created":"2024-11-29","cited_by_count":7,"area":null},{"id":"2510.24784","title":"Sub-microsecond Transformers for Jet Tagging on FPGAs","created":"2025-10-26","cited_by_count":6,"area":null},{"id":"2409.05207","title":"Low Latency Transformer Inference on FPGAs for Physics Applications with hls4ml","created":"2024-09-08","cited_by_count":5,"area":null},{"id":"2501.05515","title":"Neural Architecture Codesign for Fast Physics Applications","created":"2025-01-09","cited_by_count":5,"area":null},{"id":"2301.11810","title":"BOMP-NAS: Bayesian Optimization Mixed Precision NAS","created":"2023-01-27","cited_by_count":4,"area":null},{"id":"2302.07612","title":"Towards Optimal Compression: Joint Pruning and Quantization","created":"2023-02-15","cited_by_count":4,"area":null},{"id":"2402.02043","title":"A Plug-in Tiny AI Module for Intelligent and Selective Sensor Data Transmission","created":"2024-02-03","cited_by_count":4,"area":null},{"id":"2404.00103","title":"PikeLPN: Mitigating Overlooked Inefficiencies of Low-Precision Neural Networks","created":"2024-03-29","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":"2304.12829","title":"Improving Robustness Against Adversarial Attacks with Deeply Quantized Neural Networks","created":"2023-04-25","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":"2312.00388","title":"LinguaLinked: A Distributed Large Language Model Inference System for Mobile Devices","created":"2023-12-01","cited_by_count":3,"area":"inference"},{"id":"2601.17215","title":"JetFormer: A Scalable and Efficient Transformer for Jet Tagging from Offline Analysis to FPGA Triggers","created":"2026-01-23","cited_by_count":3,"area":null},{"id":"2202.10570","title":"Energy-Efficient Respiratory Anomaly Detection in Premature Newborn Infants","created":"2022-02-21","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":"2205.02568","title":"DropTrack -- automatic droplet tracking using deep learning for microfluidic applications","created":"2022-05-05","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":"2402.03363","title":"Exploring Prime Number Classification: Achieving High Recall Rate and Rapid Convergence with Sparse Encoding","created":"2024-01-30","cited_by_count":2,"area":null},{"id":"2406.19522","title":"Reliable edge machine learning hardware for scientific applications","created":"2024-06-27","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":"2503.12829","title":"SparseLUT: Sparse Connectivity Optimization for Lookup Table-based Deep Neural Networks","created":"2025-03-17","cited_by_count":2,"area":null},{"id":"2511.05615","title":"wa-hls4ml: A Benchmark and Surrogate Models for hls4ml Resource and Latency Estimation","created":"2025-11-06","cited_by_count":2,"area":null},{"id":"2604.07037","title":"Towards foundation-style models for energy-frontier heterogeneous neutrino detectors via self-supervised pre-training","created":"2026-04-08","cited_by_count":2,"area":null},{"id":"2206.00065","title":"FELARE: Fair Scheduling of Machine Learning Tasks on Heterogeneous Edge Systems","created":"2022-05-31","cited_by_count":1,"area":null},{"id":"2206.06780","title":"Memory-Oriented Design-Space Exploration of Edge-AI Hardware for XR Applications","created":"2022-06-08","cited_by_count":1,"area":null},{"id":"2306.04712","title":"Differentiable Earth Mover's Distance for Data Compression at the High-Luminosity LHC","created":"2023-06-07","cited_by_count":1,"area":null},{"id":"2311.05870","title":"Automated Heterogeneous Low-Bit Quantization of Multi-Model Deep Learning Inference Pipeline","created":"2023-11-10","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":"2508.02718","title":"SleepLiteCNN: Energy-Efficient Sleep Apnea Subtype Classification with 1-Second Resolution Using Single-Lead ECG","created":"2025-08-01","cited_by_count":1,"area":null},{"id":"2604.22293","title":"HGQ-LUT: Fast LUT-Aware Training and Efficient Architectures for DNN Inference","created":"2026-04-24","cited_by_count":1,"area":null},{"id":"2607.14293","title":"Real-Time Detection of Charge Jumps in Superconducting Qubits with a Convolutional Neural Network","created":"2026-07-15","cited_by_count":1,"area":null},{"id":"2208.02645","title":"Neural network accelerator for quantum control","created":"2022-08-04","cited_by_count":0,"area":null},{"id":"2210.03671","title":"A Closer Look at Hardware-Friendly Weight Quantization","created":"2022-10-07","cited_by_count":0,"area":null},{"id":"2312.05978","title":"Neural Architecture Codesign for Fast Bragg Peak Analysis","created":"2023-12-10","cited_by_count":0,"area":null},{"id":"2401.12350","title":"Scaling Up Quantization-Aware Neural Architecture Search for Efficient Deep Learning on the Edge","created":"2024-01-22","cited_by_count":0,"area":null},{"id":"2404.14436","title":"Investigating Resource-efficient Neutron/Gamma Classification ML Models Targeting eFPGAs","created":"2024-04-19","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":"2503.08973","title":"Quantitative Analysis of Deeply Quantized Tiny Neural Networks Robust to Adversarial Attacks","created":"2025-03-12","cited_by_count":0,"area":null},{"id":"2508.11664","title":"Energy-Efficient Real-Time 4-Stage Sleep Classification at 10-Second Resolution","created":"2025-08-06","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":"2511.05479","title":"Quantization Effects of Artificial Neural Networks for Embedded Edge-Computing Applications","created":"2025-11-07","cited_by_count":0,"area":null},{"id":"2512.06208","title":"SparsePixels: Efficient Convolution for Sparse Data on FPGAs","created":"2025-12-05","cited_by_count":0,"area":null},{"id":"2601.09773","title":"Enhancing LUT-based Deep Neural Networks Inference through Architecture and Connectivity Optimization","created":"2026-01-14","cited_by_count":0,"area":null},{"id":"2601.11447","title":"IMS: Intelligent Hardware Monitoring System for Secure SoCs","created":"2026-01-16","cited_by_count":0,"area":null},{"id":"2603.08722","title":"ALADIN: Accuracy-Latency-Aware Design-space Inference Analysis for Embedded AI Accelerators","created":"2026-02-12","cited_by_count":0,"area":null},{"id":"2603.26595","title":"PQuantML: A Tool for End-to-End Hardware-aware Model Compression","created":"2026-03-27","cited_by_count":0,"area":null},{"id":"2605.10612","title":"Reconfigurable Computing Challenge: Real-Time Graph Neural Networks for Online Event Selection in Big Science","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2609.04490","title":"When Quantization Breaks Memory: Recurrent-State Write-Back in Low-Precision Temporal Inference","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.23141","title":"Real-Time Plasma State Prediction via FPGA-Accelerated Quantized Recurrent Probabilistic Neural Networks","created":"2026-09-19","cited_by_count":0,"area":null},{"id":"2609.23385","title":"Leveraging Industrial Foundation Models at the Edge of Particle Physics Detectors via Distillation Learning and Hardware Co-design","created":"2026-09-20","cited_by_count":0,"area":null}],"next_cursor":null}