{"total":59,"rows":[{"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":"2103.06995","title":"Performance of a Geometric Deep Learning Pipeline for HL-LHC Particle Tracking","created":"2021-03-11","cited_by_count":30,"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":"2310.04621","title":"Model Compression in Practice: Lessons Learned from Practitioners Creating On-device Machine Learning Experiences","created":"2023-10-06","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":"2404.04815","title":"Allo: A Programming Model for Composable Accelerator Design","created":"2024-04-07","cited_by_count":16,"area":null},{"id":"2303.13569","title":"TinyML: Tools, Applications, Challenges, and Future Research Directions","created":"2023-03-23","cited_by_count":14,"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":"2203.12852","title":"Graph Neural Networks in Particle Physics: Implementations, Innovations, and Challenges","created":"2022-03-23","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":"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":"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":"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":"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":"2507.04535","title":"da4ml: Distributed Arithmetic for Real-time Neural Networks on FPGAs","created":"2025-07-06","cited_by_count":8,"area":null},{"id":"2301.07247","title":"Tailor: Altering Skip Connections for Resource-Efficient Inference","created":"2023-01-18","cited_by_count":6,"area":null},{"id":"2402.01047","title":"Ultra Fast Transformers on FPGAs for Particle Physics Experiments","created":"2024-02-01","cited_by_count":6,"area":null},{"id":"2404.03085","title":"Talaria: Interactively Optimizing Machine Learning Models for Efficient Inference","created":"2024-04-03","cited_by_count":6,"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":"2409.09044","title":"ElasticAI: Creating and Deploying Energy-Efficient Deep Learning Accelerator for Pervasive Computing","created":"2024-08-29","cited_by_count":5,"area":null},{"id":"2506.18927","title":"From Tiny Machine Learning to Tiny Deep Learning: A Survey","created":"2025-06-21","cited_by_count":5,"area":null},{"id":"2512.15946","title":"AIE4ML: An End-to-End Framework for Compiling Neural Networks for the Next Generation of AMD AI Engines","created":"2025-12-17","cited_by_count":5,"area":null},{"id":"2308.06849","title":"When Monte-Carlo Dropout Meets Multi-Exit: Optimizing Bayesian Neural Networks on FPGA","created":"2023-08-13","cited_by_count":4,"area":null},{"id":"2408.05314","title":"rule4ml: An Open-Source Tool for Resource Utilization and Latency Estimation for ML Models on FPGA","created":"2024-08-09","cited_by_count":3,"area":null},{"id":"2509.06580","title":"AI for Scientific Discovery is a Social Problem","created":"2025-09-08","cited_by_count":3,"area":null},{"id":"2209.12391","title":"FastStamp: Accelerating Neural Steganography and Digital Watermarking of Images on FPGAs","created":"2022-09-26","cited_by_count":2,"area":null},{"id":"2403.10686","title":"AutoHLS: Learning to Accelerate Design Space Exploration for HLS Designs","created":"2024-03-15","cited_by_count":2,"area":null},{"id":"2405.00738","title":"HLSTransform: Energy-Efficient Llama 2 Inference on FPGAs Via High Level Synthesis","created":"2024-04-29","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":"2601.19941","title":"Bench4HLS: End-to-End Evaluation of LLMs in High-Level Synthesis Code Generation","created":"2026-01-16","cited_by_count":2,"area":null},{"id":"2111.14767","title":"A Graph Deep Learning Framework for High-Level Synthesis Design Space Exploration","created":"2021-11-29","cited_by_count":1,"area":null},{"id":"2407.08681","title":"Hardware Neural Control of CartPole and F1TENTH Race Car","created":"2024-07-11","cited_by_count":1,"area":null},{"id":"2512.22139","title":"HLS4PC: A Parametrizable Framework For Accelerating Point-Based 3D Point Cloud Models on FPGA","created":"2025-12-11","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":"2602.15751","title":"Enabling Low-Latency Machine learning on Radiation-Hard FPGAs with hls4ml","created":"2026-02-17","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":"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":"2606.10008","title":"Spiking Neural Network inference on FPGAs with hls4ml","created":"2026-06-08","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":"2403.18921","title":"SMOF: Streaming Modern CNNs on FPGAs with Smart Off-Chip Eviction","created":"2024-03-27","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":"2406.14593","title":"Enhancing Dropout-based Bayesian Neural Networks with Multi-Exit on FPGA","created":"2024-06-20","cited_by_count":0,"area":null},{"id":"2406.16198","title":"Hardware-Aware Neural Dropout Search for Reliable Uncertainty Prediction on FPGA","created":"2024-06-23","cited_by_count":0,"area":null},{"id":"2412.17571","title":"HPCNeuroNet: A Neuromorphic Approach Merging SNN Temporal Dynamics with Transformer Attention for FPGA-based Particle Physics","created":"2024-12-23","cited_by_count":0,"area":null},{"id":"2508.21739","title":"Neural Network Acceleration on MPSoC board: Integrating SLAC's SNL, Rogue Software and Auto-SNL","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":"2511.12592","title":"Knowledge is Overrated: A zero-knowledge machine learning and cryptographic hashing-based framework for verifiable, low latency inference at the LHC","created":"2025-11-16","cited_by_count":0,"area":null},{"id":"2512.07808","title":"LUNA: LUT-Based Neural Architecture for Fast and Low-Cost Qubit Readout","created":"2025-12-08","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":"2602.02056","title":"Ultrafast On-Chip Online Learning via Spline Locality in Kolmogorov-Arnold Networks","created":"2026-02-02","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},{"id":"2603.08726","title":"Data-Rate-Aware High-Speed CNN Inference on FPGAs","created":"2026-02-18","cited_by_count":0,"area":null},{"id":"2604.08474","title":"Quantization Impact on the Accuracy and Communication Efficiency Trade-off in Federated Learning for Aerospace Predictive Maintenance","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2604.14987","title":"AI-Enabled Covert Channel Detection in RF Receiver Architectures","created":"2026-04-16","cited_by_count":0,"area":null},{"id":"2604.19106","title":"Design Rules for Extreme-Edge Scientific Computing on AI Engines","created":"2026-04-21","cited_by_count":0,"area":null},{"id":"2607.11585","title":"Machine Learning-Based Reconstruction for Resistive Silicon Sensors","created":"2026-07-13","cited_by_count":0,"area":null},{"id":"2609.09254","title":"DiffLUT-Net: Differentiable Training of FPGA LUT Networks with Learnable Connectivity","created":"2026-09-08","cited_by_count":0,"area":null}],"next_cursor":null}