{"total":27,"rows":[{"id":"2108.08810","title":"Do Vision Transformers See Like Convolutional Neural Networks?","created":"2021-08-19","cited_by_count":675,"area":null},{"id":"2105.03824","title":"FNet: Mixing Tokens with Fourier Transforms","created":"2021-05-09","cited_by_count":347,"area":null},{"id":"2205.05131","title":"UL2: Unifying Language Learning Paradigms","created":"2022-05-10","cited_by_count":295,"area":null},{"id":"2109.10686","title":"Scale Efficiently: Insights from Pre-training and Fine-tuning Transformers","created":"2021-09-22","cited_by_count":106,"area":null},{"id":"2105.13880","title":"Knowledge Inheritance for Pre-trained Language Models","created":"2021-05-28","cited_by_count":38,"area":null},{"id":"2311.05908","title":"FlashFFTConv: Efficient Convolutions for Long Sequences with Tensor Cores","created":"2023-11-10","cited_by_count":33,"area":null},{"id":"2212.10769","title":"Uncontrolled Lexical Exposure Leads to Overestimation of Compositional Generalization in Pretrained Models","created":"2022-12-21","cited_by_count":26,"area":null},{"id":"2111.13087","title":"BoxeR: Box-Attention for 2D and 3D Transformers","created":"2021-11-25","cited_by_count":23,"area":null},{"id":"2407.11435","title":"Genomic Language Models: Opportunities and Challenges","created":"2024-07-16","cited_by_count":20,"area":null},{"id":"2208.01182","title":"Mitigating Biases in Student Performance Prediction via Attention-Based Personalized Federated Learning","created":"2022-08-02","cited_by_count":13,"area":null},{"id":"2110.08975","title":"Deep Transfer Learning & Beyond: Transformer Language Models in Information Systems Research","created":"2021-10-18","cited_by_count":7,"area":null},{"id":"2212.02666","title":"Transformers for End-to-End InfoSec Tasks: A Feasibility Study","created":"2022-12-05","cited_by_count":6,"area":null},{"id":"2109.14797","title":"Emergency Vehicles Audio Detection and Localization in Autonomous Driving","created":"2021-09-30","cited_by_count":5,"area":null},{"id":"2109.15101","title":"Compositional generalization in semantic parsing with pretrained transformers","created":"2021-09-30","cited_by_count":5,"area":null},{"id":"2210.14037","title":"Revisiting Softmax for Uncertainty Approximation in Text Classification","created":"2022-10-25","cited_by_count":4,"area":null},{"id":"2301.10444","title":"An Experimental Study on Pretraining Transformers from Scratch for IR","created":"2023-01-25","cited_by_count":3,"area":null},{"id":"2505.01475","title":"CodeSSM: Towards State Space Models for Code Understanding","created":"2025-05-02","cited_by_count":3,"area":null},{"id":"2202.11937","title":"Compositional Generalization Requires Compositional Parsers","created":"2022-02-24","cited_by_count":2,"area":null},{"id":"2309.10713","title":"Interpret Vision Transformers as ConvNets with Dynamic Convolutions","created":"2023-09-19","cited_by_count":2,"area":null},{"id":"2503.06743","title":"X-GAN: A Generative AI-Powered Unsupervised Model for Main Vessel Segmentation of Glaucoma Screening","created":"2025-03-09","cited_by_count":2,"area":null},{"id":"2110.08536","title":"Sparse Distillation: Speeding Up Text Classification by Using Bigger Student Models","created":"2021-10-16","cited_by_count":1,"area":null},{"id":"2209.03834","title":"Pre-Training a Graph Recurrent Network for Language Representation","created":"2022-09-08","cited_by_count":1,"area":null},{"id":"2308.07661","title":"Attention Is Not All You Need Anymore","created":"2023-08-15","cited_by_count":1,"area":null},{"id":"2206.11187","title":"Automated Compliance Blueprint Optimization with Artificial Intelligence","created":"2022-06-22","cited_by_count":0,"area":null},{"id":"2401.12295","title":"Cheap Learning: Maximising Performance of Language Models for Social Data Science Using Minimal Data","created":"2024-01-22","cited_by_count":0,"area":null},{"id":"2409.19104","title":"Responsible AI in Open Ecosystems: Reconciling Innovation with Risk Assessment and Disclosure","created":"2024-09-27","cited_by_count":0,"area":null},{"id":"2502.12458","title":"An Empirical Evaluation of Encoder Architectures for Fast Real-Time Long Conversational Understanding","created":"2025-02-18","cited_by_count":0,"area":null}],"next_cursor":null}