{"total":24,"rows":[{"id":"2111.05849","title":"Advances in Neural Rendering","created":"2021-11-10","cited_by_count":365,"area":null},{"id":"2306.12517","title":"FFCV: Accelerating Training by Removing Data Bottlenecks","created":"2023-06-21","cited_by_count":49,"area":null},{"id":"2203.15455","title":"WeNet 2.0: More Productive End-to-End Speech Recognition Toolkit","created":"2022-03-29","cited_by_count":47,"area":null},{"id":"2209.10785","title":"Deep Lake: a Lakehouse for Deep Learning","created":"2022-09-22","cited_by_count":13,"area":null},{"id":"2211.04908","title":"Profiling and Improving the PyTorch Dataloader for high-latency Storage: A Technical Report","created":"2022-11-09","cited_by_count":5,"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":"2401.04338","title":"G-Meta: Distributed Meta Learning in GPU Clusters for Large-Scale Recommender Systems","created":"2024-01-09","cited_by_count":4,"area":null},{"id":"2505.12513","title":"GlobalGeoTree: A Multi-Granular Vision-Language Dataset for Global Tree Species Classification","created":"2025-05-18","cited_by_count":4,"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":"2404.10386","title":"I/O in Machine Learning Applications on HPC Systems: A 360-degree Survey","created":"2024-04-16","cited_by_count":3,"area":null},{"id":"2506.01883","title":"scDataset: Scalable Data Loading for Deep Learning on Large-Scale Single-Cell Omics","created":"2025-06-02","cited_by_count":1,"area":null},{"id":"2510.12617","title":"Same model, better performance: the impact of shuffling on DNA Language Models benchmarking","created":"2025-10-14","cited_by_count":1,"area":null},{"id":"2604.20357","title":"SignDATA: Data Pipeline for Sign Language Translation","created":"2026-04-22","cited_by_count":1,"area":null},{"id":"2206.00649","title":"Differentiable programming for functional connectomics","created":"2022-05-31","cited_by_count":0,"area":null},{"id":"2209.05152","title":"Detecting Network-based Internet Censorship via Latent Feature Representation Learning","created":"2022-09-12","cited_by_count":0,"area":null},{"id":"2309.01640","title":"Corgi^2: A Hybrid Offline-Online Approach To Storage-Aware Data Shuffling For SGD","created":"2023-09-04","cited_by_count":0,"area":null},{"id":"2401.14675","title":"Multi-model learning by sequential reading of untrimmed videos for action recognition","created":"2024-01-26","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":"2602.22434","title":"GetBatch: Distributed Multi-Object Retrieval for ML Data Loading","created":"2026-02-25","cited_by_count":0,"area":null},{"id":"2605.09994","title":"BatchWeave: A Consistent Object-Store-Native Data Plane for Large Foundation Model Training","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2606.29975","title":"Atompack: A Storage and Distribution Layer for Read-Heavy Atomistic ML Training Datasets","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2607.28880","title":"LayoutBench: Performance Benchmarking of Cloud Storage Layouts for Multimedia Data","created":"2026-07-30","cited_by_count":0,"area":null},{"id":"2608.27029","title":"FoldPipe: Bounded Remote Streaming of Native Molecular Shards with Asynchronous Prefetch","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2610.03087","title":"Zephon: Elastic Determinism for Online, Stateful Foundation Model Data Loading Pipelines","created":"2026-10-02","cited_by_count":0,"area":null}],"next_cursor":null}