{"total":79,"rows":[{"id":"2111.00364","title":"Sustainable AI: Environmental Implications, Challenges and Opportunities","created":"2021-10-30","cited_by_count":242,"area":null},{"id":"2203.12533","title":"Pathways: Asynchronous Distributed Dataflow for ML","created":"2022-03-23","cited_by_count":82,"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":"2403.01876","title":"D\\'ej\\`aVu: KV-cache Streaming for Fast, Fault-tolerant Generative LLM Serving","created":"2024-03-04","cited_by_count":48,"area":"inference"},{"id":"2403.07648","title":"Characterization of Large Language Model Development in the Datacenter","created":"2024-03-12","cited_by_count":46,"area":null},{"id":"2304.03271","title":"Making AI Less \"Thirsty\": Uncovering and Addressing the Secret Water Footprint of AI Models","created":"2023-04-06","cited_by_count":44,"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":"2201.07705","title":"GEMEL: Model Merging for Memory-Efficient, Real-Time Video Analytics at the Edge","created":"2022-01-19","cited_by_count":32,"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":"2505.09999","title":"ServeGen: Workload Characterization and Generation of Large Language Model Serving in Production","created":"2025-05-15","cited_by_count":29,"area":"inference"},{"id":"2410.21680","title":"Revisiting Reliability in Large-Scale Machine Learning Research Clusters","created":"2024-10-29","cited_by_count":28,"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":"2103.00686","title":"Accelerating Recommendation System Training by Leveraging Popular Choices","created":"2021-03-01","cited_by_count":22,"area":null},{"id":"2201.06227","title":"Egeria: Efficient DNN Training with Knowledge-Guided Layer Freezing","created":"2022-01-17","cited_by_count":22,"area":null},{"id":"2312.06902","title":"Reducing Energy Bloat in Large Model Training","created":"2023-12-12","cited_by_count":22,"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":"2509.16293","title":"Robust LLM Training Infrastructure at ByteDance","created":"2025-09-19","cited_by_count":16,"area":null},{"id":"2302.08545","title":"THC: Accelerating Distributed Deep Learning Using Tensor Homomorphic Compression","created":"2023-02-16","cited_by_count":15,"area":null},{"id":"2312.05385","title":"Apparate: Rethinking Early Exits to Tame Latency-Throughput Tensions in ML Serving","created":"2023-12-08","cited_by_count":15,"area":"inference"},{"id":"2310.02784","title":"MAD Max Beyond Single-Node: Enabling Large Machine Learning Model Acceleration on Distributed Systems","created":"2023-10-04","cited_by_count":14,"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":"2204.05436","title":"Heterogeneous Acceleration Pipeline for Recommendation System Training","created":"2022-04-11","cited_by_count":13,"area":null},{"id":"2312.11819","title":"An Adaptive Placement and Parallelism Framework for Accelerating RLHF Training","created":"2023-12-19","cited_by_count":13,"area":"alignment"},{"id":"2608.00101","title":"Agentic Coding in the Wild: Characterizing GitHub Copilot Traces at Production Scale","created":"2026-07-30","cited_by_count":11,"area":"agents"},{"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":"2407.00125","title":"A Survey on Failure Analysis and Fault Injection in AI Systems","created":"2024-06-28","cited_by_count":10,"area":null},{"id":"2308.12908","title":"POLCA: Power Oversubscription in LLM Cloud Providers","created":"2023-08-24","cited_by_count":9,"area":null},{"id":"2504.15465","title":"LithOS: An Operating System for Efficient Machine Learning on GPUs","created":"2025-04-21","cited_by_count":9,"area":null},{"id":"2108.02037","title":"The MIT Supercloud Dataset","created":"2021-08-04","cited_by_count":7,"area":null},{"id":"2108.03645","title":"Online Evolutionary Batch Size Orchestration for Scheduling Deep Learning Workloads in GPU Clusters","created":"2021-08-08","cited_by_count":7,"area":null},{"id":"2201.12423","title":"Benchmarking Resource Usage for Efficient Distributed Deep Learning","created":"2022-01-28","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":"2209.06018","title":"An Analysis of Collocation on GPUs for Deep Learning Training","created":"2022-09-13","cited_by_count":6,"area":null},{"id":"2509.03018","title":"Mycroft: Tracing Dependencies in Collective Communication Towards Reliable LLM Training","created":"2025-09-03","cited_by_count":6,"area":null},{"id":"2111.14247","title":"A Survey of Large-Scale Deep Learning Serving System Optimization: Challenges and Opportunities","created":"2021-11-28","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":"2204.05839","title":"The MIT Supercloud Workload Classification Challenge","created":"2022-04-12","cited_by_count":3,"area":null},{"id":"2412.15411","title":"Sparse Checkpointing for Fast and Reliable MoE Training","created":"2024-12-19","cited_by_count":3,"area":"moe"},{"id":"2503.19779","title":"PyGraph: Robust Compiler Support for CUDA Graphs in PyTorch","created":"2025-03-25","cited_by_count":3,"area":null},{"id":"2105.05080","title":"ANDREAS: Artificial intelligence traiNing scheDuler foR accElerAted resource clusterS","created":"2021-05-11","cited_by_count":2,"area":null},{"id":"2111.10672","title":"Doing More by Doing Less: How Structured Partial Backpropagation Improves Deep Learning Clusters","created":"2021-11-20","cited_by_count":2,"area":null},{"id":"2211.16648","title":"COMET: A Comprehensive Cluster Design Methodology for Distributed Deep Learning Training","created":"2022-11-30","cited_by_count":2,"area":null},{"id":"2306.11800","title":"Inshrinkerator: Compressing Deep Learning Training Checkpoints via Dynamic Quantization","created":"2023-06-20","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":"2108.09615","title":"Apache Submarine: A Unified Machine Learning Platform Made Simple","created":"2021-08-22","cited_by_count":1,"area":null},{"id":"2207.04202","title":"Smart Multi-tenant Federated Learning","created":"2022-07-09","cited_by_count":1,"area":null},{"id":"2211.15226","title":"RAMP: A Flat Nanosecond Optical Network and MPI Operations for Distributed Deep Learning Systems","created":"2022-11-28","cited_by_count":1,"area":null},{"id":"2307.07066","title":"Can Blockchains Reliably Train Machine Learning Models?","created":"2023-07-13","cited_by_count":1,"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":"2502.15940","title":"Orthogonal Calibration for Asynchronous Federated Learning","created":"2025-02-21","cited_by_count":1,"area":null},{"id":"2503.10918","title":"Resource Heterogeneity-Aware and Utilization-Enhanced Scheduling for Deep Learning Clusters","created":"2025-03-13","cited_by_count":1,"area":null},{"id":"2604.14552","title":"DEEP-GAP: Deep-learning Evaluation of Execution Parallelism in GPU Architectural Performance","created":"2026-04-16","cited_by_count":1,"area":null},{"id":"2608.06046","title":"ML-for-ML","created":"2026-08-06","cited_by_count":1,"area":null},{"id":"2110.00929","title":"Scheduling Optimization Techniques for Neural Network Training","created":"2021-10-03","cited_by_count":0,"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":"2201.06398","title":"Efficient Data-Plane Memory Scheduling for In-Network Aggregation","created":"2022-01-17","cited_by_count":0,"area":null},{"id":"2303.04086","title":"NEPHELE: A Neural Platform for Highly Realistic Cloud Radiance Rendering","created":"2023-03-07","cited_by_count":0,"area":null},{"id":"2311.10359","title":"FIKIT: Priority-Based Real-time GPU Multi-tasking Scheduling with Kernel Identification","created":"2023-11-17","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":"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":"2408.04812","title":"A Collaborative PIM Computing Optimization Framework for Multi-Tenant DNN","created":"2024-08-09","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":"2510.08522","title":"DYNAMIX: RL-based Adaptive Batch Size Optimization in Distributed Machine Learning Systems","created":"2025-10-09","cited_by_count":0,"area":"deeprl"},{"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":"2512.10980","title":"Reducing Fragmentation and Starvation in GPU Clusters through Dynamic Multi-Objective Scheduling","created":"2025-12-04","cited_by_count":0,"area":null},{"id":"2605.04478","title":"CCL-D: A High-Precision Diagnostic System for Slow and Hang Anomalies in Large-Scale Model Training","created":"2026-05-06","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":"2605.11215","title":"ReCoVer: Resilient LLM Pre-Training System via Fault-Tolerant Collective and Versatile Workload","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.19945","title":"GEM: GPU-Variability-Aware Expert to GPU Mapping for MoE Systems","created":"2026-05-19","cited_by_count":0,"area":"moe"},{"id":"2607.01409","title":"GPUAlert: A Zero-Instrumentation Process-Boundary Monitor for Diagnosing GPU Training-Job Failures","created":"2026-07-01","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":"2607.19349","title":"FineServe: A Fine-Grained Dataset and Characterization of Global LLM Serving Workloads","created":"2026-04-17","cited_by_count":0,"area":"inference"},{"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":"2609.04417","title":"Tuning Collective Patterns to Alleviate Congestion in Shared AI Clusters","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.18519","title":"COMPASS-ABS: Reducing Fragmentation in Shared GPU Clusters for Deep Learning Training Workloads","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.23321","title":"Co-occurrence Patterns of LoRA Adapters in Production Diffusion Model Inference Services","created":"2026-09-20","cited_by_count":0,"area":"diffusion"}],"next_cursor":null}