{"total":16,"rows":[{"id":"2403.07648","title":"Characterization of Large Language Model Development in the Datacenter","created":"2024-03-12","cited_by_count":46,"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":"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":"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":"2412.07894","title":"Hydraulis: Balancing Large Transformer Model Training via Co-designing Parallel Strategies and Data Assignment","created":"2024-12-10","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":"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":"2404.08901","title":"Bullion: A Column Store for Machine Learning","created":"2024-04-13","cited_by_count":1,"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":"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":"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":"2609.13922","title":"Minibatch persistency, eight years later: what batch reuse costs in steps and joules, and what it saves in data","created":"2026-09-12","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}