{"total":13,"rows":[{"id":"2307.08621","title":"Retentive Network: A Successor to Transformer for Large Language Models","created":"2023-07-17","cited_by_count":613,"area":null},{"id":"2303.11331","title":"EVA-02: A Visual Representation for Neon Genesis","created":"2023-03-20","cited_by_count":381,"area":null},{"id":"2307.02486","title":"LongNet: Scaling Transformers to 1,000,000,000 Tokens","created":"2023-07-05","cited_by_count":204,"area":null},{"id":"2310.11453","title":"BitNet: Scaling 1-bit Transformers for Large Language Models","created":"2023-10-17","cited_by_count":189,"area":null},{"id":"2307.13721","title":"Foundational Models Defining a New Era in Vision: A Survey and Outlook","created":"2023-07-25","cited_by_count":110,"area":null},{"id":"2309.11419","title":"KOSMOS-2.5: A Multimodal Literate Model","created":"2023-09-20","cited_by_count":96,"area":null},{"id":"2504.12285","title":"BitNet b1.58 2B4T Technical Report","created":"2025-04-16","cited_by_count":38,"area":null},{"id":"2405.05237","title":"EVA-X: A Foundation Model for General Chest X-ray Analysis with Self-supervised Learning","created":"2024-05-08","cited_by_count":25,"area":null},{"id":"2310.18605","title":"TorchDEQ: A Library for Deep Equilibrium Models","created":"2023-10-28","cited_by_count":21,"area":null},{"id":"2302.01327","title":"Dual PatchNorm","created":"2023-02-02","cited_by_count":9,"area":null},{"id":"2401.03246","title":"SeqNAS: Neural Architecture Search for Event Sequence Classification","created":"2024-01-06","cited_by_count":8,"area":null},{"id":"2309.01005","title":"RevColV2: Exploring Disentangled Representations in Masked Image Modeling","created":"2023-09-02","cited_by_count":4,"area":null},{"id":"2502.19008","title":"Binary Neural Networks for Large Language Model: A Survey","created":"2025-02-26","cited_by_count":1,"area":null}],"next_cursor":null}