{"total":28,"rows":[{"id":"2304.01433","title":"TPU v4: An Optically Reconfigurable Supercomputer for Machine Learning with Hardware Support for Embeddings","created":"2023-04-04","cited_by_count":202,"area":null},{"id":"2208.08489","title":"Understanding Scaling Laws for Recommendation Models","created":"2022-08-17","cited_by_count":38,"area":null},{"id":"2312.06902","title":"Reducing Energy Bloat in Large Model Training","created":"2023-12-12","cited_by_count":22,"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":"2204.05436","title":"Heterogeneous Acceleration Pipeline for Recommendation System Training","created":"2022-04-11","cited_by_count":13,"area":null},{"id":"2211.05239","title":"RecD: Deduplication for End-to-End Deep Learning Recommendation Model Training Infrastructure","created":"2022-11-09","cited_by_count":9,"area":null},{"id":"2311.13712","title":"Data Acquisition: A New Frontier in Data-centric AI","created":"2023-11-22","cited_by_count":9,"area":null},{"id":"2406.05303","title":"Beyond Efficiency: Scaling AI Sustainably","created":"2024-06-08","cited_by_count":8,"area":null},{"id":"2207.00588","title":"CoVA: Exploiting Compressed-Domain Analysis to Accelerate Video Analytics","created":"2022-07-02","cited_by_count":6,"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":"2301.04122","title":"Mystique: Enabling Accurate and Scalable Generation of Production AI Benchmarks","created":"2022-12-16","cited_by_count":5,"area":null},{"id":"2312.06254","title":"Modyn: Data-Centric Machine Learning Pipeline Orchestration","created":"2023-12-11","cited_by_count":5,"area":null},{"id":"2508.05640","title":"Request-Only Optimization for Recommendation Systems","created":"2025-07-24","cited_by_count":5,"area":null},{"id":"2301.02959","title":"FlexShard: Flexible Sharding for Industry-Scale Sequence Recommendation Models","created":"2023-01-08","cited_by_count":4,"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":"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":"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":"2402.04032","title":"ProactivePIM: Accelerating Weight-Sharing Embedding Layer with PIM for Scalable Recommendation System","created":"2024-02-06","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":"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":"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}],"next_cursor":null}