{"total":40,"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":"2403.07648","title":"Characterization of Large Language Model Development in the Datacenter","created":"2024-03-12","cited_by_count":46,"area":null},{"id":"2307.09619","title":"Towards Federated Foundation Models: Scalable Dataset Pipelines for Group-Structured Learning","created":"2023-07-18","cited_by_count":29,"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":"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":"2206.00136","title":"End-to-end Optimization of Machine Learning Prediction Queries","created":"2022-05-31","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":"2312.06254","title":"Modyn: Data-Centric Machine Learning Pipeline Orchestration","created":"2023-12-11","cited_by_count":5,"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":"2504.09844","title":"MegaScale-Data: Scaling Dataloader for Multisource Large Foundation Model Training","created":"2025-04-14","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":"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":"2501.12407","title":"The Streaming Batch Model for Efficient and Fault-Tolerant Heterogeneous Execution","created":"2025-01-16","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":"2502.06982","title":"Machine Learning Fleet Efficiency: Analyzing and Optimizing Large-Scale Google TPU Systems with ML Productivity Goodput","created":"2025-02-10","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":"2404.08901","title":"Bullion: A Column Store for Machine Learning","created":"2024-04-13","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":"2502.17060","title":"Analytics Modelling over Multiple Datasets using Vector Embeddings","created":"2025-02-24","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":"2206.09649","title":"A Machine Learning Data Fusion Model for Soil Moisture Retrieval","created":"2022-06-20","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":"2210.08650","title":"Accelerating Transfer Learning with Near-Data Computation on Cloud Object Stores","created":"2022-10-16","cited_by_count":0,"area":null},{"id":"2405.20247","title":"KerasCV and KerasNLP: Vision and Language Power-Ups","created":"2024-05-30","cited_by_count":0,"area":null},{"id":"2409.14912","title":"Efficient Tabular Data Preprocessing of ML Pipelines","created":"2024-09-23","cited_by_count":0,"area":null},{"id":"2501.12032","title":"Accelerating Recommender Model ETL with a Streaming FPGA-GPU Dataflow","created":"2025-01-21","cited_by_count":0,"area":null},{"id":"2508.03676","title":"MaLV-OS: Rethinking the Operating System Architecture for Machine Learning in Virtualized Clouds","created":"2025-08-05","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":"2603.16945","title":"Joint Optimization of Storage and Loading for High-Performance 3D Point Cloud Data Processing","created":"2026-03-16","cited_by_count":0,"area":null},{"id":"2604.24806","title":"Versioned Late Materialization for Ultra-Long Sequence Training in Recommendation Systems at Scale","created":"2026-04-27","cited_by_count":0,"area":null},{"id":"2605.09994","title":"BatchWeave: A Consistent Object-Store-Native Data Plane for Large Foundation Model Training","created":"2026-05-11","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":"2608.27029","title":"FoldPipe: Bounded Remote Streaming of Native Molecular Shards with Asynchronous Prefetch","created":"2026-08-27","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}