{"total":24,"rows":[{"id":"2202.07896","title":"Aryl: An Elastic Cluster Scheduler for Deep Learning","created":"2022-02-16","cited_by_count":27,"area":null},{"id":"2308.14363","title":"Mobile Foundation Model as Firmware","created":"2023-08-28","cited_by_count":25,"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":"2205.12095","title":"DNNAbacus: Toward Accurate Computational Cost Prediction for Deep Neural Networks","created":"2022-05-24","cited_by_count":4,"area":null},{"id":"2509.22832","title":"Efficient Fine-Grained GPU Performance Modeling for Distributed Deep Learning of LLM","created":"2025-09-26","cited_by_count":4,"area":null},{"id":"2311.09690","title":"CDMPP: A Device-Model Agnostic Framework for Latency Prediction of Tensor Programs","created":"2023-11-16","cited_by_count":3,"area":null},{"id":"2402.16731","title":"PyGim: An Efficient Graph Neural Network Library for Real Processing-In-Memory Architectures","created":"2024-02-26","cited_by_count":3,"area":null},{"id":"2407.02327","title":"QSync: Quantization-Minimized Synchronous Distributed Training Across Hybrid Devices","created":"2024-07-02","cited_by_count":3,"area":null},{"id":"2606.28565","title":"KernelSight-LM: A Kernel-Level LLM Inference Simulator","created":"2026-06-26","cited_by_count":2,"area":null},{"id":"2210.02620","title":"Inference Latency Prediction at the Edge","created":"2022-10-06","cited_by_count":1,"area":null},{"id":"2303.11733","title":"DIPPM: a Deep Learning Inference Performance Predictive Model using Graph Neural Networks","created":"2023-03-21","cited_by_count":1,"area":null},{"id":"2312.04025","title":"Moirai: Towards Optimal Placement for Distributed Inference on Heterogeneous Devices","created":"2023-12-07","cited_by_count":1,"area":null},{"id":"2401.12261","title":"Cloud-based XAI Services for Assessing Open Repository Models Under Adversarial Attacks","created":"2024-01-22","cited_by_count":1,"area":null},{"id":"2404.12674","title":"Towards Universal Performance Modeling for Machine Learning Training on Multi-GPU Platforms","created":"2024-04-19","cited_by_count":1,"area":null},{"id":"2412.15519","title":"PreNeT: Leveraging Computational Features to Predict Deep Neural Network Training Time","created":"2024-12-20","cited_by_count":1,"area":null},{"id":"2503.20191","title":"Maya: Optimizing Deep Learning Training Workloads using GPU Runtime Emulation","created":"2025-03-26","cited_by_count":1,"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":"2506.02787","title":"Rethinking Dynamic Networks and Heterogeneous Computing with Automatic Parallelization","created":"2025-06-03","cited_by_count":0,"area":null},{"id":"2511.04162","title":"ScaleDL: Towards Scalable and Efficient Runtime Prediction for Distributed Deep Learning Workloads","created":"2025-11-06","cited_by_count":0,"area":null},{"id":"2606.22013","title":"Load Testing for Machine Learning Model Serving Systems at Scale","created":"2026-06-20","cited_by_count":0,"area":null},{"id":"2606.26383","title":"SOLAR: AI-Powered Speed-of-Light Performance Analysis","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2607.02558","title":"MLSYSIM: First-Principles Infrastructure Modeling for Machine Learning Systems","created":"2026-06-28","cited_by_count":0,"area":null},{"id":"2608.18503","title":"LLM-Powered Predictive Decision-Making for Sustainable Data Center Operations","created":"2026-08-19","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}],"next_cursor":null}