{"total":16,"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":"2105.12842","title":"A Full-Stack Search Technique for Domain Optimized Deep Learning Accelerators","created":"2021-05-26","cited_by_count":19,"area":null},{"id":"2106.14089","title":"Accelerating Recurrent Neural Networks for Gravitational Wave Experiments","created":"2021-06-26","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":"2205.14510","title":"Q-LIC: Quantizing Learned Image Compression with Channel Splitting","created":"2022-05-28","cited_by_count":10,"area":null},{"id":"2211.02052","title":"Theta-Resonance: A Single-Step Reinforcement Learning Method for Design Space Exploration","created":"2022-11-03","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":"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":"2308.11334","title":"DeepBurning-MixQ: An Open Source Mixed-Precision Neural Network Accelerator Design Framework for FPGAs","created":"2023-08-22","cited_by_count":3,"area":null},{"id":"2411.03697","title":"TATAA: Programmable Mixed-Precision Transformer Acceleration with a Transformable Arithmetic Architecture","created":"2024-11-06","cited_by_count":3,"area":null},{"id":"2502.08807","title":"InTAR: Inter-Task Auto-Reconfigurable Accelerator Design for High Data Volume Variation in DNNs","created":"2025-02-12","cited_by_count":3,"area":null},{"id":"2103.04958","title":"F-CAD: A Framework to Explore Hardware Accelerators for Codec Avatar Decoding","created":"2021-03-08","cited_by_count":2,"area":null},{"id":"2506.11441","title":"DPUV4E: High-Throughput DPU Architecture Design for CNN on Versal ACAP","created":"2025-06-13","cited_by_count":2,"area":null},{"id":"2208.00800","title":"GANDSE: Generative Adversarial Network based Design Space Exploration for Neural Network Accelerator Design","created":"2022-08-01","cited_by_count":1,"area":null},{"id":"2510.24985","title":"FaRAccel: FPGA-Accelerated Defense Architecture for Efficient Bit-Flip Attack Resilience in Transformer Models","created":"2025-10-28","cited_by_count":1,"area":null},{"id":"2607.22038","title":"Sparse by Command: Task-Conditional Compute Skipping for Multi-Task Inference Accelerators","created":"2026-07-24","cited_by_count":0,"area":null}],"next_cursor":null}