{"total":20,"rows":[{"id":"2102.00527","title":"A Runtime-Based Computational Performance Predictor for Deep Neural Network Training","created":"2021-01-31","cited_by_count":29,"area":null},{"id":"2110.11466","title":"MLPerf HPC: A Holistic Benchmark Suite for Scientific Machine Learning on HPC Systems","created":"2021-10-21","cited_by_count":15,"area":null},{"id":"2202.06512","title":"Benchmarking of DL Libraries and Models on Mobile Devices","created":"2022-02-14","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":"2201.12423","title":"Benchmarking Resource Usage for Efficient Distributed Deep Learning","created":"2022-01-28","cited_by_count":7,"area":null},{"id":"2209.08938","title":"Accelerating Neural Network Inference with Processing-in-DRAM: From the Edge to the Cloud","created":"2022-09-19","cited_by_count":5,"area":null},{"id":"2301.04122","title":"Mystique: Enabling Accurate and Scalable Generation of Production AI Benchmarks","created":"2022-12-16","cited_by_count":5,"area":null},{"id":"2303.02384","title":"Hierarchical Training of Deep Neural Networks Using Early Exiting","created":"2023-03-04","cited_by_count":5,"area":null},{"id":"2104.08335","title":"Demystifying BERT: Implications for Accelerator Design","created":"2021-04-14","cited_by_count":3,"area":null},{"id":"2302.07946","title":"Experimenting with Emerging RISC-V Systems for Decentralised Machine Learning","created":"2023-02-15","cited_by_count":3,"area":null},{"id":"2404.04118","title":"GNNBENCH: Fair and Productive Benchmarking for Single-GPU GNN System","created":"2024-04-05","cited_by_count":3,"area":null},{"id":"2404.10386","title":"I/O in Machine Learning Applications on HPC Systems: A 360-degree Survey","created":"2024-04-16","cited_by_count":3,"area":null},{"id":"2304.14226","title":"TorchBench: Benchmarking PyTorch with High API Surface Coverage","created":"2023-04-27","cited_by_count":2,"area":null},{"id":"2511.05614","title":"An MLCommons Scientific Benchmarks Ontology","created":"2025-11-06","cited_by_count":2,"area":null},{"id":"2209.13705","title":"An Overview of the Data-Loader Landscape: Comparative Performance Analysis","created":"2022-09-27","cited_by_count":1,"area":null},{"id":"2301.00407","title":"MIGPerf: A Comprehensive Benchmark for Deep Learning Training and Inference Workloads on Multi-Instance GPUs","created":"2023-01-01","cited_by_count":1,"area":null},{"id":"2403.12981","title":"Beyond Inference: Performance Analysis of DNN Server Overheads for Computer Vision","created":"2024-03-02","cited_by_count":1,"area":null},{"id":"2103.04852","title":"A Case for 3D Integrated System Design for Neuromorphic Computing & AI Applications","created":"2021-03-02","cited_by_count":0,"area":null},{"id":"2207.09315","title":"Metadata Representations for Queryable ML Model Zoos","created":"2022-07-19","cited_by_count":0,"area":null},{"id":"2609.05418","title":"Benchmarking Storage Systems for Machine Learning Workloads Using NIO Bench","created":"2026-04-25","cited_by_count":0,"area":null}],"next_cursor":null}