{"total":79,"rows":[{"id":"2212.07143","title":"Reproducible scaling laws for contrastive language-image learning","created":"2022-12-14","cited_by_count":1173,"area":null},{"id":"2501.13928","title":"Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass","created":"2025-01-23","cited_by_count":367,"area":null},{"id":"2312.03863","title":"Efficient Large Language Models: A Survey","created":"2023-12-06","cited_by_count":186,"area":null},{"id":"2312.03718","title":"Large Language Models in Law: A Survey","created":"2023-11-26","cited_by_count":128,"area":null},{"id":"2110.14883","title":"Colossal-AI: A Unified Deep Learning System For Large-Scale Parallel Training","created":"2021-10-28","cited_by_count":96,"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":"2211.13878","title":"Galvatron: Efficient Transformer Training over Multiple GPUs Using Automatic Parallelism","created":"2022-11-25","cited_by_count":53,"area":null},{"id":"2303.14006","title":"ASTRA-sim2.0: Modeling Hierarchical Networks and Disaggregated Systems for Large-model Training at Scale","created":"2023-03-24","cited_by_count":47,"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":"2211.00216","title":"Distributed Graph Neural Network Training: A Survey","created":"2022-11-01","cited_by_count":32,"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":"2410.07265","title":"A Survey: Collaborative Hardware and Software Design in the Era of Large Language Models","created":"2024-10-08","cited_by_count":23,"area":null},{"id":"2201.12023","title":"Alpa: Automating Inter- and Intra-Operator Parallelism for Distributed Deep Learning","created":"2022-01-28","cited_by_count":20,"area":null},{"id":"2412.01523","title":"FlexSP: Accelerating Large Language Model Training via Flexible Sequence Parallelism","created":"2024-12-02","cited_by_count":19,"area":null},{"id":"2309.10285","title":"Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity","created":"2023-09-19","cited_by_count":17,"area":null},{"id":"2404.14712","title":"ORBIT: Oak Ridge Base Foundation Model for Earth System Predictability","created":"2024-04-23","cited_by_count":17,"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":"2406.10707","title":"DataStates-LLM: Lazy Asynchronous Checkpointing for Large Language Models","created":"2024-06-15","cited_by_count":16,"area":null},{"id":"2111.10635","title":"HeterPS: Distributed Deep Learning With Reinforcement Learning Based Scheduling in Heterogeneous Environments","created":"2021-11-20","cited_by_count":15,"area":null},{"id":"2301.09830","title":"Optimus-CC: Efficient Large NLP Model Training with 3D Parallelism Aware Communication Compression","created":"2023-01-24","cited_by_count":15,"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":"2411.07854","title":"Tucano: Advancing Neural Text Generation for Portuguese","created":"2024-11-12","cited_by_count":13,"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":"2302.08005","title":"Slapo: A Schedule Language for Progressive Optimization of Large Deep Learning Model Training","created":"2023-02-16","cited_by_count":11,"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":"2502.21231","title":"ByteScale: Efficient Scaling of LLM Training with a 2048K Context Length on More Than 12,000 GPUs","created":"2025-02-28","cited_by_count":10,"area":null},{"id":"2505.04802","title":"ORBIT-2: Scaling Exascale Vision Foundation Models for Weather and Climate Downscaling","created":"2025-05-07","cited_by_count":10,"area":null},{"id":"2110.07554","title":"Looper: An end-to-end ML platform for product decisions","created":"2021-10-14","cited_by_count":9,"area":null},{"id":"2111.05894","title":"Graph Neural Network Training with Data Tiering","created":"2021-11-10","cited_by_count":8,"area":null},{"id":"2402.11215","title":"AdAdaGrad: Adaptive Batch Size Schemes for Adaptive Gradient Methods","created":"2024-02-17","cited_by_count":8,"area":null},{"id":"2406.12909","title":"Scalable Training of Trustworthy and Energy-Efficient Predictive Graph Foundation Models for Atomistic Materials Modeling: A Case Study with HydraGNN","created":"2024-06-12","cited_by_count":8,"area":null},{"id":"2408.09574","title":"PhysBERT: A Text Embedding Model for Physics Scientific Literature","created":"2024-08-18","cited_by_count":8,"area":null},{"id":"2411.13055","title":"Hardware Scaling Trends and Diminishing Returns in Large-Scale Distributed Training","created":"2024-11-20","cited_by_count":8,"area":null},{"id":"2306.08881","title":"Evaluation and Optimization of Gradient Compression for Distributed Deep Learning","created":"2023-06-15","cited_by_count":7,"area":null},{"id":"2401.07788","title":"Activations and Gradients Compression for Model-Parallel Training","created":"2024-01-15","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":"2501.16986","title":"Generative quantum combinatorial optimization by means of a novel conditional generative quantum eigensolver","created":"2025-01-28","cited_by_count":7,"area":null},{"id":"2212.05611","title":"Accelerating Self-Supervised Learning via Efficient Training Strategies","created":"2022-12-11","cited_by_count":5,"area":null},{"id":"2503.17469","title":"OmniLearn: A Framework for Distributed Deep Learning over Heterogeneous Clusters","created":"2025-03-21","cited_by_count":5,"area":null},{"id":"2509.10371","title":"Characterizing the Efficiency of Distributed Training: A Power, Performance, and Thermal Perspective","created":"2025-09-12","cited_by_count":5,"area":null},{"id":"2504.09844","title":"MegaScale-Data: Scaling Dataloader for Multisource Large Foundation Model Training","created":"2025-04-14","cited_by_count":4,"area":null},{"id":"2302.12445","title":"DeAR: Accelerating Distributed Deep Learning with Fine-Grained All-Reduce Pipelining","created":"2023-02-24","cited_by_count":3,"area":null},{"id":"2308.14258","title":"Breaking Boundaries: Distributed Domain Decomposition with Scalable Physics-Informed Neural PDE Solvers","created":"2023-08-28","cited_by_count":3,"area":null},{"id":"2309.16743","title":"High Throughput Training of Deep Surrogates from Large Ensemble Runs","created":"2023-09-28","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":"2412.18052","title":"Beyond Gradient Averaging in Parallel Optimization: Improved Robustness through Gradient Agreement Filtering","created":"2024-12-24","cited_by_count":3,"area":null},{"id":"2501.11847","title":"A Survey on Memory-Efficient Transformer-Based Model Training in AI for Science","created":"2025-01-21","cited_by_count":3,"area":null},{"id":"2507.11683","title":"PGT-I: Scaling Spatiotemporal GNNs with Memory-Efficient Distributed Training","created":"2025-07-15","cited_by_count":3,"area":null},{"id":"2509.00015","title":"MedFormer: a data-driven model for forecasting the Mediterranean Sea","created":"2025-08-16","cited_by_count":2,"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":"2210.07454","title":"Communication-Efficient Adam-Type Algorithms for Distributed Data Mining","created":"2022-10-14","cited_by_count":1,"area":null},{"id":"2210.09147","title":"PARTIME: Scalable and Parallel Processing Over Time with Deep Neural Networks","created":"2022-10-17","cited_by_count":1,"area":null},{"id":"2403.11204","title":"Partitioned Neural Network Training via Synthetic Intermediate Labels","created":"2024-03-17","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":"2405.19338","title":"Accurate Patient Alignment without Unnecessary Imaging Dose via Synthesizing Patient-specific 3D CT Images from 2D kV Images","created":"2024-04-01","cited_by_count":1,"area":null},{"id":"2406.13984","title":"Reducing Memory Contention and I/O Congestion for Disk-based GNN Training","created":"2024-06-20","cited_by_count":1,"area":null},{"id":"2406.18254","title":"Improving the Consistency in Cross-Lingual Cross-Modal Retrieval with 1-to-K Contrastive Learning","created":"2024-06-26","cited_by_count":1,"area":null},{"id":"2410.07352","title":"Generating Origin-Destination Matrices in Neural Spatial Interaction Models","created":"2024-10-09","cited_by_count":1,"area":null},{"id":"2410.08256","title":"AdaShadow: Responsive Test-time Model Adaptation in Non-stationary Mobile Environments","created":"2024-10-10","cited_by_count":1,"area":null},{"id":"2511.10480","title":"Scalable Synthesis of distributed LLM workloads through Symbolic Tensor Graphs","created":"2025-11-13","cited_by_count":1,"area":null},{"id":"2512.17499","title":"Validation of Diagnostic Artificial Intelligence Models for Prostate Pathology in a Middle Eastern Cohort","created":"2025-12-19","cited_by_count":1,"area":null},{"id":"2604.04736","title":"Sampling Parallelism for Fast and Efficient Bayesian Learning","created":"2026-04-06","cited_by_count":1,"area":null},{"id":"2103.07974","title":"CrossoverScheduler: Overlapping Multiple Distributed Training Applications in a Crossover Manner","created":"2021-03-14","cited_by_count":0,"area":null},{"id":"2202.13491","title":"Sparsity-aware neural user behavior modeling in online interaction platforms","created":"2022-02-28","cited_by_count":0,"area":null},{"id":"2304.00737","title":"SparDL: Distributed Deep Learning Training with Efficient Sparse Communication","created":"2023-04-03","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":"2404.02300","title":"SDT-GNN: Streaming-based Distributed Training Framework for Graph Neural Networks","created":"2024-04-02","cited_by_count":0,"area":null},{"id":"2408.11746","title":"Mixed Sparsity Training: Achieving 4$\\times$ FLOP Reduction for Transformer Pretraining","created":"2024-08-21","cited_by_count":0,"area":null},{"id":"2504.18658","title":"The Big Send-off: Scalable and Performant Collectives for Deep Learning","created":"2025-04-25","cited_by_count":0,"area":null},{"id":"2506.20818","title":"Demystifying Distributed Training of Graph Neural Networks for Link Prediction","created":"2025-06-25","cited_by_count":0,"area":null},{"id":"2508.00960","title":"A Parallel Alternative for Energy-Efficient Neural Network Training and Inferencing","created":"2025-08-01","cited_by_count":0,"area":null},{"id":"2510.26151","title":"MV-MLM: Bridging Multi-View Mammography and Language for Breast Cancer Diagnosis and Risk Prediction","created":"2025-10-30","cited_by_count":0,"area":null},{"id":"2602.02632","title":"Performance of Small Language Model Pretraining on FABRIC: An Empirical Study","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2603.08211","title":"Revisiting Gradient Staleness: Evaluating Distance Metrics for Asynchronous Federated Learning Aggregation","created":"2026-03-09","cited_by_count":0,"area":null},{"id":"2603.27341","title":"A Comparative Study in Surgical AI: Potential and Limitations of Data, Compute, and Scaling","created":"2026-03-28","cited_by_count":0,"area":null},{"id":"2605.21603","title":"DynaFlow: Transparent and Flexible Intra-Device Parallelism via Programmable Operator Scheduling","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2607.16053","title":"Deep and Probabilistic Models for Gene Regulatory Network Inference","created":"2026-07-17","cited_by_count":0,"area":null},{"id":"2608.02168","title":"Empowering Credit Risk Detection in Weixin Pay with Billion-Scale Deep Graph Learning","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2610.11954","title":"Look Where You Can: Active View Selection for CAD Reconstruction under Occlusion","created":"2026-10-08","cited_by_count":0,"area":null}],"next_cursor":null}