{"total":108,"rows":[{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673,"area":null},{"id":"2104.04473","title":"Efficient Large-Scale Language Model Training on GPU Clusters Using Megatron-LM","created":"2021-04-09","cited_by_count":632,"area":null},{"id":"2111.00364","title":"Sustainable AI: Environmental Implications, Challenges and Opportunities","created":"2021-10-30","cited_by_count":242,"area":null},{"id":"2105.11367","title":"FedScale: Benchmarking Model and System Performance of Federated Learning at Scale","created":"2021-05-24","cited_by_count":136,"area":null},{"id":"2203.02714","title":"Towards Efficient and Scalable Sharpness-Aware Minimization","created":"2022-03-05","cited_by_count":129,"area":null},{"id":"2204.00595","title":"Monarch: Expressive Structured Matrices for Efficient and Accurate Training","created":"2022-04-01","cited_by_count":106,"area":null},{"id":"2110.12894","title":"The Efficiency Misnomer","created":"2021-10-25","cited_by_count":98,"area":null},{"id":"2207.10062","title":"DataPerf: Benchmarks for Data-Centric AI Development","created":"2022-07-20","cited_by_count":90,"area":null},{"id":"2110.01406","title":"MedPerf: Open Benchmarking Platform for Medical Artificial Intelligence using Federated Evaluation","created":"2021-09-29","cited_by_count":88,"area":null},{"id":"2104.05158","title":"Software-Hardware Co-design for Fast and Scalable Training of Deep Learning Recommendation Models","created":"2021-04-12","cited_by_count":78,"area":null},{"id":"2404.12241","title":"Introducing v0.5 of the AI Safety Benchmark from MLCommons","created":"2024-04-18","cited_by_count":62,"area":null},{"id":"2502.06559","title":"Can We Trust AI Benchmarks? An Interdisciplinary Review of Current Issues in AI Evaluation","created":"2025-02-10","cited_by_count":60,"area":null},{"id":"2106.11872","title":"Randomness In Neural Network Training: Characterizing The Impact of Tooling","created":"2021-06-22","cited_by_count":59,"area":null},{"id":"2101.11714","title":"TT-Rec: Tensor Train Compression for Deep Learning Recommendation Models","created":"2021-01-25","cited_by_count":58,"area":null},{"id":"2211.09760","title":"VeLO: Training Versatile Learned Optimizers by Scaling Up","created":"2022-11-17","cited_by_count":57,"area":null},{"id":"2306.12517","title":"FFCV: Accelerating Training by Removing Data Bottlenecks","created":"2023-06-21","cited_by_count":49,"area":null},{"id":"2101.12127","title":"tf.data: A Machine Learning Data Processing Framework","created":"2021-01-28","cited_by_count":41,"area":null},{"id":"2107.08147","title":"AutoFL: Enabling Heterogeneity-Aware Energy Efficient Federated Learning","created":"2021-07-16","cited_by_count":39,"area":null},{"id":"2103.03239","title":"Moshpit SGD: Communication-Efficient Decentralized Training on Heterogeneous Unreliable Devices","created":"2021-03-04","cited_by_count":36,"area":null},{"id":"2211.00216","title":"Distributed Graph Neural Network Training: A Survey","created":"2022-11-01","cited_by_count":32,"area":null},{"id":"2102.00527","title":"A Runtime-Based Computational Performance Predictor for Deep Neural Network Training","created":"2021-01-31","cited_by_count":29,"area":null},{"id":"2108.09373","title":"Understanding Data Storage and Ingestion for Large-Scale Deep Recommendation Model Training","created":"2021-08-20","cited_by_count":28,"area":null},{"id":"2201.10095","title":"RecShard: Statistical Feature-Based Memory Optimization for Industry-Scale Neural Recommendation","created":"2022-01-25","cited_by_count":28,"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":"2304.04640","title":"NeuroBench: A Framework for Benchmarking Neuromorphic Computing Algorithms and Systems","created":"2023-04-10","cited_by_count":27,"area":null},{"id":"2309.11932","title":"A Machine Learning-oriented Survey on Tiny Machine Learning","created":"2023-09-21","cited_by_count":27,"area":null},{"id":"2103.00543","title":"On the Utility of Gradient Compression in Distributed Training Systems","created":"2021-02-28","cited_by_count":26,"area":null},{"id":"2106.00958","title":"A Generalizable Approach to Learning Optimizers","created":"2021-06-02","cited_by_count":23,"area":null},{"id":"2512.03024","title":"TokenPowerBench: Benchmarking the Power Consumption of LLM Inference","created":"2025-12-02","cited_by_count":22,"area":null},{"id":"2306.15552","title":"A Survey on Deep Learning Hardware Accelerators for Heterogeneous HPC Platforms","created":"2023-06-27","cited_by_count":21,"area":null},{"id":"2102.06356","title":"A Large Batch Optimizer Reality Check: Traditional, Generic Optimizers Suffice Across Batch Sizes","created":"2021-02-12","cited_by_count":20,"area":null},{"id":"2111.04131","title":"Plumber: Diagnosing and Removing Performance Bottlenecks in Machine Learning Data Pipelines","created":"2021-11-07","cited_by_count":16,"area":null},{"id":"2308.13490","title":"TpuGraphs: A Performance Prediction Dataset on Large Tensor Computational Graphs","created":"2023-08-25","cited_by_count":16,"area":null},{"id":"2410.12032","title":"MLPerf Power: Benchmarking the Energy Efficiency of Machine Learning Systems from Microwatts to Megawatts for Sustainable AI","created":"2024-10-15","cited_by_count":16,"area":null},{"id":"2101.02342","title":"User Response Prediction in Online Advertising","created":"2021-01-07","cited_by_count":15,"area":null},{"id":"2110.11466","title":"MLPerf HPC: A Holistic Benchmark Suite for Scientific Machine Learning on HPC Systems","created":"2021-10-21","cited_by_count":15,"area":null},{"id":"2110.15032","title":"OneFlow: Redesign the Distributed Deep Learning Framework from Scratch","created":"2021-10-28","cited_by_count":15,"area":null},{"id":"2103.02886","title":"Improving Computational Efficiency in Visual Reinforcement Learning via Stored Embeddings","created":"2021-03-04","cited_by_count":12,"area":null},{"id":"2202.06512","title":"Benchmarking of DL Libraries and Models on Mobile Devices","created":"2022-02-14","cited_by_count":12,"area":null},{"id":"2106.00221","title":"Concurrent Adversarial Learning for Large-Batch Training","created":"2021-06-01","cited_by_count":11,"area":null},{"id":"2107.04991","title":"Prediction Surface Uncertainty Quantification in Object Detection Models for Autonomous Driving","created":"2021-07-11","cited_by_count":10,"area":null},{"id":"2201.07821","title":"Building a Performance Model for Deep Learning Recommendation Model Training on GPUs","created":"2022-01-19","cited_by_count":10,"area":null},{"id":"2202.12429","title":"BagPipe: Accelerating Deep Recommendation Model Training","created":"2022-02-24","cited_by_count":10,"area":null},{"id":"2201.04768","title":"On Sampling Collaborative Filtering Datasets","created":"2022-01-13","cited_by_count":8,"area":null},{"id":"2305.05843","title":"MoCA: Memory-Centric, Adaptive Execution for Multi-Tenant Deep Neural Networks","created":"2023-05-10","cited_by_count":8,"area":null},{"id":"2402.16565","title":"Partial Rankings of Optimizers","created":"2024-02-26","cited_by_count":8,"area":null},{"id":"2506.01774","title":"Greening AI-enabled Systems with Software Engineering: A Research Agenda for Environmentally Sustainable AI Practices","created":"2025-06-02","cited_by_count":8,"area":null},{"id":"2102.02344","title":"Horizontally Fused Training Array: An Effective Hardware Utilization Squeezer for Training Novel Deep Learning Models","created":"2021-02-03","cited_by_count":7,"area":null},{"id":"2105.12676","title":"Low-Precision Hardware Architectures Meet Recommendation Model Inference at Scale","created":"2021-05-26","cited_by_count":7,"area":null},{"id":"2111.04949","title":"A Survey and Empirical Evaluation of Parallel Deep Learning Frameworks","created":"2021-11-09","cited_by_count":7,"area":null},{"id":"2102.13243","title":"Swift for TensorFlow: A portable, flexible platform for deep learning","created":"2021-02-26","cited_by_count":6,"area":null},{"id":"2111.04779","title":"ML-EXray: Visibility into ML Deployment on the Edge","created":"2021-11-08","cited_by_count":6,"area":null},{"id":"2204.07288","title":"Characterizing the Efficiency vs. Accuracy Trade-off for Long-Context NLP Models","created":"2022-04-15","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":"2102.04285","title":"RL-Scope: Cross-Stack Profiling for Deep Reinforcement Learning Workloads","created":"2021-02-08","cited_by_count":5,"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":"2508.13898","title":"Beyond the Mean: Fisher-Orthogonal Projection for Natural Gradient Descent in Large Batch Training","created":"2025-08-19","cited_by_count":5,"area":null},{"id":"2601.09527","title":"Private LLM Inference on Consumer Blackwell GPUs: A Practical Guide for Cost-Effective Local Deployment in SMEs","created":"2026-01-14","cited_by_count":5,"area":null},{"id":"2204.06240","title":"CowClip: Reducing CTR Prediction Model Training Time from 12 hours to 10 minutes on 1 GPU","created":"2022-04-13","cited_by_count":4,"area":null},{"id":"2212.01340","title":"Moving Beyond Downstream Task Accuracy for Information Retrieval Benchmarking","created":"2022-12-02","cited_by_count":4,"area":null},{"id":"2306.03163","title":"How Can We Train Deep Learning Models Across Clouds and Continents? An Experimental Study","created":"2023-06-05","cited_by_count":4,"area":null},{"id":"2306.10598","title":"DropCompute: simple and more robust distributed synchronous training via compute variance reduction","created":"2023-06-18","cited_by_count":4,"area":null},{"id":"2504.16026","title":"Trends in AI Supercomputers","created":"2025-04-22","cited_by_count":4,"area":null},{"id":"2104.08335","title":"Demystifying BERT: Implications for Accelerator Design","created":"2021-04-14","cited_by_count":3,"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":"2404.04118","title":"GNNBENCH: Fair and Productive Benchmarking for Single-GPU GNN System","created":"2024-04-05","cited_by_count":3,"area":null},{"id":"2501.12407","title":"The Streaming Batch Model for Efficient and Fault-Tolerant Heterogeneous Execution","created":"2025-01-16","cited_by_count":3,"area":null},{"id":"2512.11588","title":"AI Benchmark Democratization and Carpentry","created":"2025-12-12","cited_by_count":3,"area":null},{"id":"2603.20174","title":"TinyML Enhances CubeSat Mission Capabilities","created":"2026-03-20","cited_by_count":3,"area":null},{"id":"2106.07454","title":"NG+ : A Multi-Step Matrix-Product Natural Gradient Method for Deep Learning","created":"2021-06-14","cited_by_count":2,"area":null},{"id":"2304.14226","title":"TorchBench: Benchmarking PyTorch with High API Surface Coverage","created":"2023-04-27","cited_by_count":2,"area":null},{"id":"2307.05741","title":"Towards Robust and Efficient Continual Language Learning","created":"2023-07-11","cited_by_count":2,"area":null},{"id":"2401.01728","title":"Ravnest: Decentralized Asynchronous Training on Heterogeneous Devices","created":"2024-01-03","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":"2403.02327","title":"Model Lakes","created":"2024-03-04","cited_by_count":2,"area":null},{"id":"2409.12994","title":"Performance and Power: Systematic Evaluation of AI Workloads on Accelerators with CARAML","created":"2024-09-19","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":"2511.05614","title":"An MLCommons Scientific Benchmarks Ontology","created":"2025-11-06","cited_by_count":2,"area":null},{"id":"2104.02188","title":"GPU Domain Specialization via Composable On-Package Architecture","created":"2021-04-05","cited_by_count":1,"area":null},{"id":"2111.05231","title":"MLHarness: A Scalable Benchmarking System for MLCommons","created":"2021-11-09","cited_by_count":1,"area":null},{"id":"2209.13705","title":"An Overview of the Data-Loader Landscape: Comparative Performance Analysis","created":"2022-09-27","cited_by_count":1,"area":null},{"id":"2303.04759","title":"RAF: Holistic Compilation for Deep Learning Model Training","created":"2023-03-08","cited_by_count":1,"area":null},{"id":"2411.03742","title":"Adaptive Consensus Gradients Aggregation for Scaled Distributed Training","created":"2024-11-06","cited_by_count":1,"area":null},{"id":"2508.13163","title":"Sustainable AI Training via Hardware-Software Co-Design on NVIDIA, AMD, and Emerging GPU Architectures","created":"2025-07-28","cited_by_count":1,"area":null},{"id":"2601.19107","title":"TinyTorch: Building Machine Learning Systems from First Principles","created":"2026-01-27","cited_by_count":1,"area":null},{"id":"2601.22108","title":"Learning What to Predict: Downstream-Guided Task Design for Continued Pretraining","created":"2026-01-29","cited_by_count":1,"area":null},{"id":"2604.07345","title":"Measurement of Generative AI Workload Power Profiles for Whole-Facility Data Center Infrastructure Planning","created":"2026-04-08","cited_by_count":1,"area":null},{"id":"2605.20799","title":"Instant GPU Efficiency Visibility at Fleet Scale","created":"2026-05-20","cited_by_count":1,"area":null},{"id":"2202.10979","title":"Enabling Reproducibility and Meta-learning Through a Lifelong Database of Experiments (LDE)","created":"2022-02-22","cited_by_count":0,"area":null},{"id":"2207.09315","title":"Metadata Representations for Queryable ML Model Zoos","created":"2022-07-19","cited_by_count":0,"area":null},{"id":"2212.03410","title":"SAIH: A Scalable Evaluation Methodology for Understanding AI Performance Trend on HPC Systems","created":"2022-12-07","cited_by_count":0,"area":null},{"id":"2312.10561","title":"Enabling Accelerators for Graph Computing","created":"2023-12-16","cited_by_count":0,"area":null},{"id":"2402.02447","title":"Breaking MLPerf Training: A Case Study on Optimizing BERT","created":"2024-02-04","cited_by_count":0,"area":null},{"id":"2406.18701","title":"Fast Optimizer Benchmark","created":"2024-06-26","cited_by_count":0,"area":null},{"id":"2407.19721","title":"Rina: Enhancing Ring-AllReduce with In-network Aggregation in Distributed Model Training","created":"2024-07-29","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":"2504.18454","title":"Pseudo-Asynchronous Local SGD: Robust and Efficient Data-Parallel Training","created":"2025-04-25","cited_by_count":0,"area":null},{"id":"2506.06235","title":"Optimizing Cloud-to-GPU Throughput for Deep Learning With Earth Observation Data","created":"2025-06-06","cited_by_count":0,"area":null},{"id":"2508.03676","title":"MaLV-OS: Rethinking the Operating System Architecture for Machine Learning in Virtualized Clouds","created":"2025-08-05","cited_by_count":0,"area":null},{"id":"2509.03263","title":"Estudio de la eficiencia en la escalabilidad de GPUs para el entrenamiento de Inteligencia Artificial","created":"2025-09-03","cited_by_count":0,"area":null}],"next_cursor":"100"}