{"total":24,"rows":[{"id":"2302.13939","title":"SpikeGPT: Generative Pre-trained Language Model with Spiking Neural Networks","created":"2023-02-27","cited_by_count":88,"area":null},{"id":"2212.14034","title":"Cramming: Training a Language Model on a Single GPU in One Day","created":"2022-12-28","cited_by_count":81,"area":null},{"id":"2102.12459","title":"When Attention Meets Fast Recurrence: Training Language Models with Reduced Compute","created":"2021-02-24","cited_by_count":34,"area":null},{"id":"2210.04243","title":"Fine-Tuning Pre-trained Transformers into Decaying Fast Weights","created":"2022-10-09","cited_by_count":26,"area":null},{"id":"2106.00958","title":"A Generalizable Approach to Learning Optimizers","created":"2021-06-02","cited_by_count":23,"area":null},{"id":"2310.16142","title":"A Language Model with Limited Memory Capacity Captures Interference in Human Sentence Processing","created":"2023-10-24","cited_by_count":22,"area":null},{"id":"2204.12406","title":"A survey on attention mechanisms for medical applications: are we moving towards better algorithms?","created":"2022-04-26","cited_by_count":15,"area":null},{"id":"2102.13136","title":"Automated essay scoring using efficient transformer-based language models","created":"2021-02-25","cited_by_count":12,"area":null},{"id":"2203.01215","title":"Mukayese: Turkish NLP Strikes Back","created":"2022-03-02","cited_by_count":9,"area":null},{"id":"2306.02870","title":"On \"Scientific Debt\" in NLP: A Case for More Rigour in Language Model Pre-Training Research","created":"2023-06-05","cited_by_count":7,"area":null},{"id":"2110.05571","title":"SRU++: Pioneering Fast Recurrence with Attention for Speech Recognition","created":"2021-10-11","cited_by_count":6,"area":null},{"id":"2109.00993","title":"LegaLMFiT: Efficient Short Legal Text Classification with LSTM Language Model Pre-Training","created":"2021-09-02","cited_by_count":4,"area":null},{"id":"2104.12424","title":"Attention vs non-attention for a Shapley-based explanation method","created":"2021-04-26","cited_by_count":3,"area":null},{"id":"2510.12327","title":"Simple Projection Variants Improve ColBERT Performance","created":"2025-10-14","cited_by_count":2,"area":null},{"id":"2405.03904","title":"Transformer models as an efficient replacement for statistical test suites to evaluate the quality of random numbers","created":"2024-05-06","cited_by_count":1,"area":null},{"id":"2502.00617","title":"Efficient Language Modeling for Low-Resource Settings with Hybrid RNN-Transformer Architectures","created":"2025-02-02","cited_by_count":1,"area":null},{"id":"2105.07520","title":"Dynamic Pooling Improves Nanopore Base Calling Accuracy","created":"2021-05-16","cited_by_count":0,"area":null},{"id":"2106.13493","title":"Online Self-Attentive Gated RNNs for Real-Time Speaker Separation","created":"2021-06-25","cited_by_count":0,"area":null},{"id":"2108.08207","title":"SHAQ: Single Headed Attention with Quasi-Recurrence","created":"2021-08-18","cited_by_count":0,"area":null},{"id":"2211.01848","title":"Circling Back to Recurrent Models of Language","created":"2022-11-03","cited_by_count":0,"area":null},{"id":"2302.02055","title":"Implicit Geometry and Interaction Embeddings Improve Few-Shot Molecular Property Prediction","created":"2023-02-04","cited_by_count":0,"area":null},{"id":"2308.03429","title":"RCMHA: Relative Convolutional Multi-Head Attention for Natural Language Modelling","created":"2023-08-07","cited_by_count":0,"area":null},{"id":"2401.09880","title":"Attention-Based Recurrent Neural Network For Automatic Behavior Laying Hen Recognition","created":"2024-01-18","cited_by_count":0,"area":null},{"id":"2401.15055","title":"Deep learning-based approach for tomato classification in complex scenes","created":"2024-01-26","cited_by_count":0,"area":null}],"next_cursor":null}