{"total":62,"rows":[{"id":"2208.06102","title":"Zeus: Understanding and Optimizing GPU Energy Consumption of DNN Training","created":"2022-08-12","cited_by_count":79,"area":null},{"id":"2504.15930","title":"StreamRL: Scalable, Heterogeneous, and Elastic RL for LLMs with Disaggregated Stream Generation","created":"2025-04-22","cited_by_count":61,"area":null},{"id":"2406.18533","title":"On Scaling Up 3D Gaussian Splatting Training","created":"2024-06-26","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":"2109.01313","title":"Characterization and Prediction of Deep Learning Workloads in Large-Scale GPU Datacenters","created":"2021-09-03","cited_by_count":31,"area":null},{"id":"2202.07896","title":"Aryl: An Elastic Cluster Scheduler for Deep Learning","created":"2022-02-16","cited_by_count":27,"area":null},{"id":"2308.00852","title":"CASSINI: Network-Aware Job Scheduling in Machine Learning Clusters","created":"2023-08-01","cited_by_count":26,"area":null},{"id":"2312.12391","title":"vTrain: A Simulation Framework for Evaluating Cost-effective and Compute-optimal Large Language Model Training","created":"2023-11-27","cited_by_count":23,"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":"2310.10046","title":"TRANSOM: An Efficient Fault-Tolerant System for Training LLMs","created":"2023-10-16","cited_by_count":13,"area":null},{"id":"2202.07848","title":"Singularity: Planet-Scale, Preemptive and Elastic Scheduling of AI Workloads","created":"2022-02-16","cited_by_count":10,"area":null},{"id":"2305.12201","title":"GraVAC: Adaptive Compression for Communication-Efficient Distributed DL Training","created":"2023-05-20","cited_by_count":10,"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":"2109.11067","title":"Serving DNN Models with Multi-Instance GPUs: A Case of the Reconfigurable Machine Scheduling Problem","created":"2021-09-18","cited_by_count":7,"area":null},{"id":"2307.07950","title":"Accelerating Distributed ML Training via Selective Synchronization","created":"2023-07-16","cited_by_count":7,"area":null},{"id":"2409.03365","title":"Spindle: Efficient Distributed Training of Multi-Task Large Models via Wavefront Scheduling","created":"2024-09-05","cited_by_count":7,"area":null},{"id":"2502.03885","title":"InfiniteHBD: Building Datacenter-Scale High-Bandwidth Domain for LLM with Optical Circuit Switching Transceivers","created":"2025-02-06","cited_by_count":7,"area":null},{"id":"2205.11913","title":"Deep Learning Workload Scheduling in GPU Datacenters: Taxonomy, Challenges and Vision","created":"2022-05-24","cited_by_count":6,"area":null},{"id":"2112.02752","title":"End-to-end Adaptive Distributed Training on PaddlePaddle","created":"2021-12-06","cited_by_count":5,"area":null},{"id":"2303.06659","title":"Scavenger: A Cloud Service for Optimizing Cost and Performance of ML Training","created":"2023-03-12","cited_by_count":5,"area":null},{"id":"2310.19991","title":"PolyThrottle: Energy-efficient Neural Network Inference on Edge Devices","created":"2023-10-30","cited_by_count":5,"area":null},{"id":"2106.12091","title":"BFTrainer: Low-Cost Training of Neural Networks on Unfillable Supercomputer Nodes","created":"2021-06-22","cited_by_count":3,"area":null},{"id":"2112.10065","title":"Efficient Strong Scaling Through Burst Parallel Training","created":"2021-12-19","cited_by_count":3,"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":"2312.02493","title":"Flexible Communication for Optimal Distributed Learning over Unpredictable Networks","created":"2023-12-05","cited_by_count":3,"area":null},{"id":"2411.15997","title":"Ensuring Fair LLM Serving Amid Diverse Applications","created":"2024-11-24","cited_by_count":3,"area":null},{"id":"2305.01519","title":"BCEdge: SLO-Aware DNN Inference Services with Adaptive Batching on Edge Platforms","created":"2023-05-01","cited_by_count":2,"area":null},{"id":"2309.01226","title":"Saturn: An Optimized Data System for Large Model Deep Learning Workloads","created":"2023-09-03","cited_by_count":2,"area":null},{"id":"2401.16492","title":"GPU Cluster Scheduling for Network-Sensitive Deep Learning","created":"2024-01-29","cited_by_count":2,"area":null},{"id":"2406.08115","title":"Resource Allocation and Workload Scheduling for Large-Scale Distributed Deep Learning: A Survey","created":"2024-06-12","cited_by_count":2,"area":null},{"id":"2310.20209","title":"Network Contention-Aware Cluster Scheduling with Reinforcement Learning","created":"2023-10-31","cited_by_count":1,"area":null},{"id":"2312.08298","title":"Venn: Resource Management for Collaborative Learning Jobs","created":"2023-12-13","cited_by_count":1,"area":null},{"id":"2404.09679","title":"AntDT: A Self-Adaptive Distributed Training Framework for Leader and Straggler Nodes","created":"2024-04-15","cited_by_count":1,"area":null},{"id":"2506.14851","title":"Efficient Serving of LLM Applications with Probabilistic Demand Modeling","created":"2025-06-17","cited_by_count":1,"area":null},{"id":"2608.06046","title":"ML-for-ML","created":"2026-08-06","cited_by_count":1,"area":null},{"id":"2609.34645","title":"Nereus: Adaptive Parallelism for LLM Post-Training","created":"2026-09-28","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":"2401.10354","title":"Towards providing reliable job completion time predictions using PCS","created":"2024-01-18","cited_by_count":0,"area":null},{"id":"2402.09589","title":"MLCC: A Congestion Control Technique to Accelerate ML Training","created":"2024-02-14","cited_by_count":0,"area":null},{"id":"2402.17652","title":"Compass: A Decentralized Scheduler for Latency-Sensitive ML Workflows","created":"2024-02-27","cited_by_count":0,"area":null},{"id":"2403.16125","title":"Arena: Efficiently Training Large Models via Dynamic Scheduling and Adaptive Parallelism Co-Design","created":"2024-03-24","cited_by_count":0,"area":null},{"id":"2412.02729","title":"Resource-Adaptive Successive Doubling for Hyperparameter Optimization with Large Datasets on High-Performance Computing Systems","created":"2024-12-03","cited_by_count":0,"area":null},{"id":"2501.05563","title":"Prediction-Assisted Online Distributed Deep Learning Workload Scheduling in GPU Clusters","created":"2025-01-09","cited_by_count":0,"area":null},{"id":"2505.01616","title":"Phantora: Maximizing Code Reuse in Simulation-based Machine Learning System Performance Estimation","created":"2025-05-02","cited_by_count":0,"area":null},{"id":"2505.12815","title":"Learning In Chaos: Efficient Autoscaling and Self-Healing for Multi-Party Distributed Training","created":"2025-05-19","cited_by_count":0,"area":null},{"id":"2508.04953","title":"Tesserae: Scalable Placement Policies for Deep Learning Workloads","created":"2025-08-07","cited_by_count":0,"area":null},{"id":"2508.19073","title":"AEGIS: Runtime-Guided GPU Collocation for Multi-Tenant Deep Learning Training","created":"2025-08-26","cited_by_count":0,"area":null},{"id":"2510.15652","title":"GOGH: Correlation-Guided Orchestration of GPUs in Heterogeneous Clusters","created":"2025-10-17","cited_by_count":0,"area":null},{"id":"2512.10271","title":"Hybrid Learning and Optimization-Based Dynamic Scheduling for DL Workloads on Heterogeneous GPU Clusters","created":"2025-12-11","cited_by_count":0,"area":null},{"id":"2512.12816","title":"Optimal Resource Allocation for ML Model Training and Deployment under Concept Drift","created":"2025-12-14","cited_by_count":0,"area":null},{"id":"2603.18112","title":"Tula: Optimizing Time, Cost, and Generalization in Distributed Large-Batch Training","created":"2026-03-18","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":"2605.18750","title":"A Readiness-Driven Runtime for Pipeline-Parallel Training under Runtime Variability","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2606.25759","title":"NEURON-Fabric: Architecture-Runtime Co-Design for Controlled Low-Bit Gradient Communication","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2607.02544","title":"Not Every Sync Is Safe: Calibrated DiLoCo Scheduling for Shared AI Infrastructure","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2608.15762","title":"Global Simulation-Guided Dynamic Operator Scheduling for Efficient Multi-Tenant Model Serving","created":"2026-08-16","cited_by_count":0,"area":null},{"id":"2608.23840","title":"ShardMeter: Sharded and Geo-Distributed Training Without the Guesswork","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2609.04417","title":"Tuning Collective Patterns to Alleviate Congestion in Shared AI Clusters","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.07236","title":"Parallelism Strategy Chaining for Fast Training Convergence","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2609.27040","title":"EMA: Elastic and Performance Transparent Memory Across GPUs","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2610.02828","title":"FSPO: Policy-Consistent Risk and Pareto-Feasible Control for Budgeted LLM RL Post-Training","created":"2026-10-02","cited_by_count":0,"area":null}],"next_cursor":null}