{"list":"other","total":55,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"2106.01946","title":"Convex optimization","created":"2021-06-03","cited_by_count":2515},{"id":"1808.06226","title":"SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing","created":"2018-08-19","cited_by_count":1989},{"id":"1904.01038","title":"fairseq: A Fast, Extensible Toolkit for Sequence Modeling","created":"2019-04-01","cited_by_count":1488},{"id":"2406.17557","title":"The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale","created":"2024-06-25","cited_by_count":1160},{"id":"1712.00409","title":"Deep Learning Scaling is Predictable, Empirically","created":"2017-12-01","cited_by_count":582},{"id":"2010.11125","title":"Beyond English-Centric Multilingual Machine Translation","created":"2020-10-21","cited_by_count":561},{"id":"2106.03193","title":"The FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translation","created":"2021-06-06","cited_by_count":560},{"id":"2010.14701","title":"Scaling Laws for Autoregressive Generative Modeling","created":"2020-10-28","cited_by_count":522},{"id":"1906.08158","title":"BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning","created":"2019-06-19","cited_by_count":432},{"id":"2305.16264","title":"Scaling Data-Constrained Language Models","created":"2023-05-25","cited_by_count":403},{"id":"2102.06701","title":"Explaining Neural Scaling Laws","created":"2021-02-12","cited_by_count":363},{"id":"2203.03466","title":"Tensor Programs V: Tuning Large Neural Networks via Zero-Shot Hyperparameter Transfer","created":"2022-03-07","cited_by_count":288},{"id":"2008.00401","title":"Multilingual Translation with Extensible Multilingual Pretraining and Finetuning","created":"2020-08-02","cited_by_count":287},{"id":"1903.00089","title":"Massively Multilingual Neural Machine Translation","created":"2019-02-28","cited_by_count":246},{"id":"1301.3666","title":"Zero-Shot Learning Through Cross-Modal Transfer","created":"2013-01-16","cited_by_count":237},{"id":"1604.02201","title":"Transfer Learning for Low-Resource Neural Machine Translation","created":"2016-04-08","cited_by_count":188},{"id":"2010.12309","title":"A Survey on Recent Approaches for Natural Language Processing in Low-Resource Scenarios","created":"2020-10-23","cited_by_count":171},{"id":"2310.03003","title":"From Words to Watts: Benchmarking the Energy Costs of Large Language Model Inference","created":"2023-10-04","cited_by_count":170},{"id":"2405.18392","title":"Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations","created":"2024-05-28","cited_by_count":170},{"id":"2209.06640","title":"Revisiting Neural Scaling Laws in Language and Vision","created":"2022-09-13","cited_by_count":132},{"id":"2109.07740","title":"Scaling Laws for Neural Machine Translation","created":"2021-09-16","cited_by_count":111},{"id":"2106.15115","title":"Neural Machine Translation for Low-Resource Languages: A Survey","created":"2021-06-29","cited_by_count":109},{"id":"2110.02095","title":"Exploring the Limits of Large Scale Pre-training","created":"2021-10-05","cited_by_count":104},{"id":"2006.07264","title":"Low-resource Languages: A Review of Past Work and Future Challenges","created":"2020-06-12","cited_by_count":91},{"id":"1406.3896","title":"Freeze-Thaw Bayesian Optimization","created":"2014-06-16","cited_by_count":90},{"id":"1808.05697","title":"Deep Bayesian Active Learning for Natural Language Processing: Results of a Large-Scale Empirical Study","created":"2018-08-16","cited_by_count":90},{"id":"2102.04074","title":"Learning Curve Theory","created":"2021-02-08","cited_by_count":85},{"id":"2309.14393","title":"LLMCarbon: Modeling the end-to-end Carbon Footprint of Large Language Models","created":"2023-09-25","cited_by_count":72},{"id":"2103.10948","title":"The Shape of Learning Curves: a Review","created":"2021-03-19","cited_by_count":70},{"id":"2410.01131","title":"nGPT: Normalized Transformer with Representation Learning on the Hypersphere","created":"2024-10-01","cited_by_count":70},{"id":"1708.09803","title":"Transfer Learning across Low-Resource, Related Languages for Neural Machine Translation","created":"2017-08-31","cited_by_count":58},{"id":"2202.01994","title":"Data Scaling Laws in NMT: The Effect of Noise and Architecture","created":"2022-02-04","cited_by_count":55},{"id":"2005.00870","title":"Predicting Performance for Natural Language Processing Tasks","created":"2020-05-02","cited_by_count":49},{"id":"1906.06669","title":"One Epoch Is All You Need","created":"2019-06-16","cited_by_count":41},{"id":"2406.12907","title":"Reconciling Kaplan and Chinchilla Scaling Laws","created":"2024-06-12","cited_by_count":39},{"id":"2310.20447","title":"Efficient Bayesian Learning Curve Extrapolation using Prior-Data Fitted Networks","created":"2023-10-31","cited_by_count":37},{"id":"2404.00459","title":"NumeroLogic: Number Encoding for Enhanced LLMs' Numerical Reasoning","created":"2024-03-30","cited_by_count":31},{"id":"2201.12150","title":"Learning Curves for Decision Making in Supervised Machine Learning: A Survey","created":"2022-01-28","cited_by_count":27},{"id":"2102.05486","title":"Towards More Fine-grained and Reliable NLP Performance Prediction","created":"2021-02-10","cited_by_count":26},{"id":"2108.07686","title":"Scaling Laws for Deep Learning","created":"2021-08-17","cited_by_count":26},{"id":"2205.10186","title":"Bayesian Active Learning with Fully Bayesian Gaussian Processes","created":"2022-05-20","cited_by_count":26},{"id":"2110.08875","title":"Predicting the Performance of Multilingual NLP Models","created":"2021-10-17","cited_by_count":24},{"id":"2203.08850","title":"Pre-Trained Multilingual Sequence-to-Sequence Models: A Hope for Low-Resource Language Translation?","created":"2022-03-16","cited_by_count":24},{"id":"2302.00441","title":"Scaling Laws for Hyperparameter Optimization","created":"2023-02-01","cited_by_count":16},{"id":"2402.02633","title":"Predicting Machine Translation Performance on Low-Resource Languages: The Role of Domain Similarity","created":"2024-02-04","cited_by_count":15},{"id":"2411.01042","title":"Introduction to AI Safety, Ethics, and Society","created":"2024-11-01","cited_by_count":15},{"id":"1705.09862","title":"Efficient Modeling of Latent Information in Supervised Learning using Gaussian Processes","created":"2017-05-27","cited_by_count":14},{"id":"2410.09239","title":"Scaling Gaussian Processes for Learning Curve Prediction via Latent Kronecker Structure","created":"2024-10-11","cited_by_count":10},{"id":"2501.16396","title":"TopoNets: High Performing Vision and Language Models with Brain-Like Topography","created":"2025-01-27","cited_by_count":10},{"id":"2308.16822","title":"Latent Variable Multi-output Gaussian Processes for Hierarchical Datasets","created":"2023-08-31","cited_by_count":3}],"next_cursor":null}