{"total":35,"rows":[{"id":"2207.10062","title":"DataPerf: Benchmarks for Data-Centric AI Development","created":"2022-07-20","cited_by_count":90,"area":null},{"id":"2306.12517","title":"FFCV: Accelerating Training by Removing Data Bottlenecks","created":"2023-06-21","cited_by_count":49,"area":null},{"id":"2101.12127","title":"tf.data: A Machine Learning Data Processing Framework","created":"2021-01-28","cited_by_count":41,"area":null},{"id":"2108.09373","title":"Understanding Data Storage and Ingestion for Large-Scale Deep Recommendation Model Training","created":"2021-08-20","cited_by_count":28,"area":null},{"id":"2103.00686","title":"Accelerating Recommendation System Training by Leveraging Popular Choices","created":"2021-03-01","cited_by_count":22,"area":null},{"id":"2201.06227","title":"Egeria: Efficient DNN Training with Knowledge-Guided Layer Freezing","created":"2022-01-17","cited_by_count":22,"area":null},{"id":"2312.06902","title":"Reducing Energy Bloat in Large Model Training","created":"2023-12-12","cited_by_count":22,"area":null},{"id":"2111.04131","title":"Plumber: Diagnosing and Removing Performance Bottlenecks in Machine Learning Data Pipelines","created":"2021-11-07","cited_by_count":16,"area":null},{"id":"2210.14826","title":"tf.data service: A Case for Disaggregating ML Input Data Processing","created":"2022-10-26","cited_by_count":16,"area":null},{"id":"2202.08679","title":"Where Is My Training Bottleneck? Hidden Trade-Offs in Deep Learning Preprocessing Pipelines","created":"2022-02-17","cited_by_count":10,"area":null},{"id":"2401.08895","title":"cedar: Optimized and Unified Machine Learning Input Data Pipelines","created":"2024-01-17","cited_by_count":6,"area":null},{"id":"2406.13768","title":"FastPersist: Accelerating Model Checkpointing in Deep Learning","created":"2024-06-19","cited_by_count":6,"area":null},{"id":"2407.12117","title":"MEMO: Fine-grained Tensor Management For Ultra-long Context LLM Training","created":"2024-07-16","cited_by_count":5,"area":null},{"id":"2409.18749","title":"TensorSocket: Shared Data Loading for Deep Learning Training","created":"2024-09-27","cited_by_count":4,"area":null},{"id":"2308.08500","title":"InTune: Reinforcement Learning-based Data Pipeline Optimization for Deep Recommendation Models","created":"2023-08-13","cited_by_count":3,"area":null},{"id":"2502.19790","title":"Mixtera: A Data Plane for Foundation Model Training","created":"2025-02-27","cited_by_count":3,"area":null},{"id":"2406.14571","title":"PreSto: An In-Storage Data Preprocessing System for Training Recommendation Models","created":"2024-06-11","cited_by_count":2,"area":null},{"id":"2502.20016","title":"Position: Neglecting the Sustainability of AI is Fuelling a Global AI Arms Race","created":"2025-02-27","cited_by_count":2,"area":null},{"id":"2509.10712","title":"MinatoLoader: Accelerating Machine Learning Training Through Efficient Data Preprocessing","created":"2025-09-12","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":"2212.07936","title":"A Study on the Intersection of GPU Utilization and CNN Inference","created":"2022-12-15","cited_by_count":1,"area":null},{"id":"2502.15712","title":"GPUs, CPUs, and... NICs: Rethinking the Network's Role in Serving Complex AI Pipelines","created":"2025-01-22","cited_by_count":1,"area":null},{"id":"2110.06073","title":"Synergy: Resource Sensitive DNN Scheduling in Multi-Tenant Clusters","created":"2021-10-12","cited_by_count":0,"area":null},{"id":"2110.14819","title":"Characterizing and Taming Resolution in Convolutional Neural Networks","created":"2021-10-28","cited_by_count":0,"area":null},{"id":"2208.08711","title":"L3: Accelerator-Friendly Lossless Image Format for High-Resolution, High-Throughput DNN Training","created":"2022-08-18","cited_by_count":0,"area":null},{"id":"2306.09293","title":"[Experiments & Analysis] Evaluating the Feasibility of Sampling-Based Techniques for Training Multilayer Perceptrons","created":"2023-06-15","cited_by_count":0,"area":null},{"id":"2411.19114","title":"PREBA: A Hardware/Software Co-Design for Multi-Instance GPU based AI Inference Servers","created":"2024-11-28","cited_by_count":0,"area":null},{"id":"2506.06235","title":"Optimizing Cloud-to-GPU Throughput for Deep Learning With Earth Observation Data","created":"2025-06-06","cited_by_count":0,"area":null},{"id":"2511.13724","title":"Preparation Meets Opportunity: Enhancing Data Preprocessing for ML Training With Seneca","created":"2025-09-24","cited_by_count":0,"area":null},{"id":"2602.22434","title":"GetBatch: Distributed Multi-Object Retrieval for ML Data Loading","created":"2026-02-25","cited_by_count":0,"area":null},{"id":"2607.02558","title":"MLSYSIM: First-Principles Infrastructure Modeling for Machine Learning Systems","created":"2026-06-28","cited_by_count":0,"area":null},{"id":"2608.22795","title":"VersaDB: A High-Performance AI Storage Database for Unifying Mutimodal Datasets","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2609.06635","title":"RGB Input Pipelines: Throughput, GPU Memory, and Transformation Coverage","created":"2026-09-06","cited_by_count":0,"area":null},{"id":"2609.24205","title":"A principled approach for energy-efficient training via phase-aware GPU frequency tuning","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2610.03087","title":"Zephon: Elastic Determinism for Online, Stateful Foundation Model Data Loading Pipelines","created":"2026-10-02","cited_by_count":0,"area":null}],"next_cursor":null}