{"total":33,"rows":[{"id":"2202.05924","title":"Compute Trends Across Three Eras of Machine Learning","created":"2022-02-11","cited_by_count":163,"area":null},{"id":"2206.01288","title":"Decentralized Training of Foundation Models in Heterogeneous Environments","created":"2022-06-02","cited_by_count":87,"area":null},{"id":"2401.08092","title":"A Survey of Resource-efficient LLM and Multimodal Foundation Models","created":"2024-01-16","cited_by_count":86,"area":null},{"id":"2204.12013","title":"Bamboo: Making Preemptible Instances Resilient for Affordable Training of Large DNNs","created":"2022-04-26","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":"2309.08125","title":"Oobleck: Resilient Distributed Training of Large Models Using Pipeline Templates","created":"2023-09-15","cited_by_count":40,"area":null},{"id":"2407.20143","title":"ByteCheckpoint: A Unified Checkpointing System for Large Foundation Model Development","created":"2024-07-29","cited_by_count":24,"area":null},{"id":"2401.02452","title":"The Compute Divide in Machine Learning: A Threat to Academic Contribution and Scrutiny?","created":"2024-01-04","cited_by_count":20,"area":null},{"id":"2411.01438","title":"SkyServe: Serving AI Models across Regions and Clouds with Spot Instances","created":"2024-11-03","cited_by_count":20,"area":null},{"id":"2312.05181","title":"Tenplex: Dynamic Parallelism for Deep Learning using Parallelizable Tensor Collections","created":"2023-12-08","cited_by_count":16,"area":null},{"id":"2401.00134","title":"Unicron: Economizing Self-Healing LLM Training at Scale","created":"2023-12-30","cited_by_count":16,"area":null},{"id":"2509.16293","title":"Robust LLM Training Infrastructure at ByteDance","created":"2025-09-19","cited_by_count":16,"area":null},{"id":"2405.14009","title":"ReCycle: Resilient Training of Large DNNs using Pipeline Adaptation","created":"2024-05-22","cited_by_count":14,"area":null},{"id":"2206.04959","title":"Merak: An Efficient Distributed DNN Training Framework with Automated 3D Parallelism for Giant Foundation Models","created":"2022-06-10","cited_by_count":11,"area":null},{"id":"2401.02643","title":"Training and Serving System of Foundation Models: A Comprehensive Survey","created":"2024-01-05","cited_by_count":11,"area":null},{"id":"2404.06114","title":"Communication-Efficient Large-Scale Distributed Deep Learning: A Comprehensive Survey","created":"2024-04-09","cited_by_count":10,"area":null},{"id":"2506.14813","title":"Training with Confidence: Catching Silent Errors in Deep Learning Training with Automated Proactive Checks","created":"2025-06-06","cited_by_count":10,"area":null},{"id":"2503.19050","title":"Mist: Efficient Distributed Training of Large Language Models via Memory-Parallelism Co-Optimization","created":"2025-03-24","cited_by_count":7,"area":null},{"id":"2202.10435","title":"Survey on Large Scale Neural Network Training","created":"2022-02-21","cited_by_count":4,"area":null},{"id":"2402.15514","title":"Large Scale Generative AI Text Applied to Sports and Music","created":"2024-01-31","cited_by_count":4,"area":null},{"id":"2411.14458","title":"Improving training time and GPU utilization in geo-distributed language model training","created":"2024-11-16","cited_by_count":3,"area":null},{"id":"2507.21276","title":"LeMix: Unified Scheduling for LLM Training and Inference on Multi-GPU Systems","created":"2025-07-28","cited_by_count":3,"area":null},{"id":"2311.15269","title":"Tessel: Boosting Distributed Execution of Large DNN Models via Flexible Schedule Search","created":"2023-11-26","cited_by_count":2,"area":null},{"id":"2211.06814","title":"Pit-Pattern Classification of Colorectal Cancer Polyps Using a Hyper Sensitive Vision-Based Tactile Sensor and Dilated Residual Networks","created":"2022-11-13","cited_by_count":1,"area":null},{"id":"2312.00843","title":"Exploring the Robustness of Decentralized Training for Large Language Models","created":"2023-12-01","cited_by_count":1,"area":null},{"id":"2409.03674","title":"Practical Forecasting of Cryptocoins Timeseries using Correlation Patterns","created":"2024-09-05","cited_by_count":1,"area":null},{"id":"2512.13728","title":"CurvaDion: Curvature-Adaptive Distributed Orthonormalization","created":"2025-12-13","cited_by_count":1,"area":null},{"id":"2601.16956","title":"DataStates-LLM: Scalable Checkpointing for Transformer Models Using Composable State Providers","created":"2026-01-23","cited_by_count":1,"area":null},{"id":"2403.12320","title":"Approximated Likelihood Ratio: A Forward-Only and Parallel Framework for Boosting Neural Network Training","created":"2024-03-18","cited_by_count":0,"area":null},{"id":"2605.09370","title":"From Detection to Recovery: Operational Analysis on LLM Pre-training with 504 GPUs","created":"2026-05-10","cited_by_count":0,"area":null},{"id":"2607.01646","title":"PHOENIX: Resilient LLM Training with Hot-Swapping via Zero-Overhead Checkpoint","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2609.22087","title":"When Is Availability-Aware Training Worth It? A Benchmark and Empirical Study of Interruption-Resilient Optimization Under Predictable Compute Schedules","created":"2026-06-22","cited_by_count":0,"area":null},{"id":"2609.39067","title":"Argus: A Real-EKS Study of When Predicting Spot Interruptions Beats Simple Checkpointing","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}