{"list":"other","total":71,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"1602.05629","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","created":"2016-02-17","cited_by_count":7669},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"2106.07447","title":"HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units","created":"2021-06-14","cited_by_count":2342},{"id":"1510.00149","title":"Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding","created":"2015-10-01","cited_by_count":2329},{"id":"2211.14730","title":"A Time Series is Worth 64 Words: Long-term Forecasting with Transformers","created":"2022-11-27","cited_by_count":2039},{"id":"1803.01271","title":"An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling","created":"2018-03-04","cited_by_count":1476},{"id":"1810.03993","title":"Model Cards for Model Reporting","created":"2018-10-05","cited_by_count":1080},{"id":"2210.02186","title":"TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis","created":"2022-10-05","cited_by_count":1058},{"id":"2103.15808","title":"CvT: Introducing Convolutions to Vision Transformers","created":"2021-03-29","cited_by_count":947},{"id":"1707.02968","title":"Revisiting Unreasonable Effectiveness of Data in Deep Learning Era","created":"2017-07-10","cited_by_count":919},{"id":"2111.11432","title":"Florence: A New Foundation Model for Computer Vision","created":"2021-11-22","cited_by_count":804},{"id":"2202.10054","title":"Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution","created":"2022-02-21","cited_by_count":739},{"id":"2302.05442","title":"Scaling Vision Transformers to 22 Billion Parameters","created":"2023-02-10","cited_by_count":694},{"id":"1611.08024","title":"EEGNet: A Compact Convolutional Network for EEG-based Brain-Computer Interfaces","created":"2016-11-23","cited_by_count":628},{"id":"1911.00359","title":"CCNet: Extracting High Quality Monolingual Datasets from Web Crawl Data","created":"2019-11-01","cited_by_count":548},{"id":"2402.03885","title":"MOMENT: A Family of Open Time-series Foundation Models","created":"2024-02-06","cited_by_count":482},{"id":"2106.14112","title":"Time-Series Representation Learning via Temporal and Contextual Contrasting","created":"2021-06-26","cited_by_count":345},{"id":"2405.18765","title":"Large Brain Model for Learning Generic Representations with Tremendous EEG Data in BCI","created":"2024-05-29","cited_by_count":327},{"id":"2208.06366","title":"BEiT v2: Masked Image Modeling with Vector-Quantized Visual Tokenizers","created":"2022-08-12","cited_by_count":303},{"id":"1905.12784","title":"Intrinsic dimension of data representations in deep neural networks","created":"2019-05-29","cited_by_count":282},{"id":"2206.08496","title":"Self-Supervised Contrastive Pre-Training For Time Series via Time-Frequency Consistency","created":"2022-06-17","cited_by_count":250},{"id":"1909.12673","title":"A Constructive Prediction of the Generalization Error Across Scales","created":"2019-09-27","cited_by_count":210},{"id":"2101.12037","title":"BENDR: using transformers and a contrastive self-supervised learning task to learn from massive amounts of EEG data","created":"2021-01-28","cited_by_count":199},{"id":"2407.13278","title":"Deep Time Series Models: A Comprehensive Survey and Benchmark","created":"2024-07-18","cited_by_count":197},{"id":"1412.6115","title":"Compressing Deep Convolutional Networks using Vector Quantization","created":"2014-12-18","cited_by_count":195},{"id":"2202.09729","title":"It's Raw! Audio Generation with State-Space Models","created":"2022-02-20","cited_by_count":171},{"id":"1901.05498","title":"Deep learning-based electroencephalography analysis: a systematic review","created":"2019-01-16","cited_by_count":156},{"id":"2110.09327","title":"Self-Supervised Representation Learning: Introduction, Advances and Challenges","created":"2021-10-18","cited_by_count":148},{"id":"2202.01575","title":"CoST: Contrastive Learning of Disentangled Seasonal-Trend Representations for Time Series Forecasting","created":"2022-02-03","cited_by_count":144},{"id":"2007.16104","title":"Uncovering the structure of clinical EEG signals with self-supervised learning","created":"2020-07-31","cited_by_count":109},{"id":"2106.11170","title":"Transformer-based Spatial-Temporal Feature Learning for EEG Decoding","created":"2021-06-11","cited_by_count":97},{"id":"2409.00101","title":"NeuroLM: A Universal Multi-task Foundation Model for Bridging the Gap between Language and EEG Signals","created":"2024-08-27","cited_by_count":88},{"id":"2104.08336","title":"Self-Supervised Graph Neural Networks for Improved Electroencephalographic Seizure Analysis","created":"2021-04-16","cited_by_count":76},{"id":"2311.03764","title":"Neuro-GPT: Towards A Foundation Model for EEG","created":"2023-11-07","cited_by_count":74},{"id":"2302.14367","title":"BrainBERT: Self-supervised representation learning for intracranial recordings","created":"2023-02-28","cited_by_count":72},{"id":"2208.02405","title":"Transformer Convolutional Neural Networks for Automated Artifact Detection in Scalp EEG","created":"2022-08-04","cited_by_count":55},{"id":"2401.10278","title":"EEGFormer: Towards Transferable and Interpretable Large-Scale EEG Foundation Model","created":"2024-01-11","cited_by_count":52},{"id":"2402.04177","title":"Scaling Laws for Downstream Task Performance of Large Language Models","created":"2024-02-06","cited_by_count":49},{"id":"2009.10365","title":"Inter-database validation of a deep learning approach for automatic sleep scoring","created":"2020-09-22","cited_by_count":38},{"id":"2410.12360","title":"Towards Neural Scaling Laws for Time Series Foundation Models","created":"2024-10-16","cited_by_count":33},{"id":"2211.11176","title":"Modeling Multivariate Biosignals With Graph Neural Networks and Structured State Space Models","created":"2022-11-21","cited_by_count":29},{"id":"2402.10251","title":"BrainWave: A Brain Signal Foundation Model for Clinical Applications","created":"2024-02-15","cited_by_count":26},{"id":"2503.00580","title":"Brain Foundation Models: A Survey on Advancements in Neural Signal Processing and Brain Discovery","created":"2025-03-01","cited_by_count":22},{"id":"2401.05446","title":"Self-supervised Learning for Electroencephalogram: A Systematic Survey","created":"2024-01-09","cited_by_count":19},{"id":"2405.13867","title":"Scaling-laws for Large Time-series Models","created":"2024-05-22","cited_by_count":18},{"id":"2209.11233","title":"Evaluating Latent Space Robustness and Uncertainty of EEG-ML Models under Realistic Distribution Shifts","created":"2022-09-22","cited_by_count":16},{"id":"2402.13005","title":"SzCORE: A Seizure Community Open-source Research Evaluation framework for the validation of EEG-based automated seizure detection algorithms","created":"2024-02-20","cited_by_count":16},{"id":"2409.12454","title":"FoME: A Foundation Model for EEG using Adaptive Temporal-Lateral Attention Scaling","created":"2024-09-19","cited_by_count":16},{"id":"2411.08343","title":"Brain Treebank: Large-scale intracranial recordings from naturalistic language stimuli","created":"2024-11-13","cited_by_count":16},{"id":"1910.10076","title":"Prediction of Reaction Time and Vigilance Variability from Spatiospectral Features of Resting-State EEG in a Long Sustained Attention Task","created":"2019-10-21","cited_by_count":15},{"id":"2503.00711","title":"OpenECG: Benchmarking ECG Foundation Models with Public 1.2 Million Records","created":"2025-03-02","cited_by_count":11},{"id":"2406.10083","title":"On the Evaluation of Speech Foundation Models for Spoken Language Understanding","created":"2024-06-14","cited_by_count":9},{"id":"2301.03470","title":"Unsupervised Multivariate Time-Series Transformers for Seizure Identification on EEG","created":"2023-01-03","cited_by_count":3},{"id":"2111.13970","title":"Label Assistant: A Workflow for Assisted Data Annotation in Image Segmentation Tasks","created":"2021-11-27","cited_by_count":1}],"next_cursor":null}