{"list":"other","total":61,"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":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2208.12242","title":"DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation","created":"2022-08-25","cited_by_count":3300},{"id":"2101.03961","title":"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity","created":"2021-01-11","cited_by_count":3073},{"id":"1409.3215","title":"Sequence to Sequence Learning with Neural Networks","created":"2014-09-10","cited_by_count":2986},{"id":"2012.07805","title":"Extracting Training Data from Large Language Models","created":"2020-12-14","cited_by_count":2189},{"id":"1909.08053","title":"Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism","created":"2019-09-17","cited_by_count":1868},{"id":"1803.02155","title":"Self-Attention with Relative Position Representations","created":"2018-03-06","cited_by_count":1120},{"id":"2209.04747","title":"Diffusion Models in Vision: A Survey","created":"2022-09-10","cited_by_count":1015},{"id":"2112.06905","title":"GLaM: Efficient Scaling of Language Models with Mixture-of-Experts","created":"2021-12-13","cited_by_count":897},{"id":"1911.00536","title":"DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation","created":"2019-11-01","cited_by_count":842},{"id":"1707.08114","title":"A Survey on Multi-Task Learning","created":"2017-07-25","cited_by_count":840},{"id":"2103.00112","title":"Transformer in Transformer","created":"2021-02-27","cited_by_count":633},{"id":"1704.04760","title":"In-Datacenter Performance Analysis of a Tensor Processing Unit","created":"2017-04-16","cited_by_count":618},{"id":"2201.11990","title":"Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Model","created":"2022-01-28","cited_by_count":559},{"id":"1911.00222","title":"Federated Learning with Differential Privacy: Algorithms and Performance Analysis","created":"2019-11-01","cited_by_count":536},{"id":"2108.08877","title":"Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text Models","created":"2021-08-19","cited_by_count":463},{"id":"2111.01243","title":"Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey","created":"2021-11-01","cited_by_count":463},{"id":"2106.13219","title":"Towards Understanding and Mitigating Social Biases in Language Models","created":"2021-06-24","cited_by_count":296},{"id":"1408.5093","title":"Caffe: Convolutional Architecture for Fast Feature Embedding","created":"2014-06-20","cited_by_count":288},{"id":"2006.11371","title":"Opportunities and Challenges in Explainable Artificial Intelligence (XAI): A Survey","created":"2020-06-16","cited_by_count":254},{"id":"2303.04226","title":"A Comprehensive Survey of AI-Generated Content (AIGC): A History of Generative AI from GAN to ChatGPT","created":"2023-03-07","cited_by_count":224},{"id":"2106.10328","title":"Process for Adapting Language Models to Society (PALMS) with Values-Targeted Datasets","created":"2021-06-18","cited_by_count":181},{"id":"1505.00487","title":"Sequence to Sequence -- Video to Text","created":"2015-05-03","cited_by_count":158},{"id":"2304.01852","title":"Summary of ChatGPT-Related Research and Perspective Towards the Future of Large Language Models","created":"2023-04-04","cited_by_count":154},{"id":"2005.14354","title":"UGC-VQA: Benchmarking Blind Video Quality Assessment for User Generated Content","created":"2020-05-29","cited_by_count":140},{"id":"1909.01380","title":"The Bottom-up Evolution of Representations in the Transformer: A Study with Machine Translation and Language Modeling Objectives","created":"2019-09-03","cited_by_count":139},{"id":"2104.12369","title":"PanGu-$\\alpha$: Large-scale Autoregressive Pretrained Chinese Language Models with Auto-parallel Computation","created":"2021-04-26","cited_by_count":134},{"id":"2311.07226","title":"Large Language Models for Robotics: A Survey","created":"2023-11-13","cited_by_count":133},{"id":"2004.12158","title":"How Does NLP Benefit Legal System: A Summary of Legal Artificial Intelligence","created":"2020-04-25","cited_by_count":129},{"id":"1911.12011","title":"JEC-QA: A Legal-Domain Question Answering Dataset","created":"2019-11-27","cited_by_count":116},{"id":"2105.03887","title":"Lawformer: A Pre-trained Language Model for Chinese Legal Long Documents","created":"2021-05-09","cited_by_count":116},{"id":"2210.15424","title":"What Language Model to Train if You Have One Million GPU Hours?","created":"2022-10-27","cited_by_count":92},{"id":"2006.15704","title":"PyTorch Distributed: Experiences on Accelerating Data Parallel Training","created":"2020-06-28","cited_by_count":90},{"id":"2208.11857","title":"Shortcut Learning of Large Language Models in Natural Language Understanding","created":"2022-08-25","cited_by_count":85},{"id":"2005.05906","title":"Why Fairness Cannot Be Automated: Bridging the Gap Between EU Non-Discrimination Law and AI","created":"2020-05-12","cited_by_count":81},{"id":"2107.09051","title":"AI in Finance: Challenges, Techniques and Opportunities","created":"2021-07-20","cited_by_count":81},{"id":"2010.04548","title":"Deep Learning for Procedural Content Generation","created":"2020-10-09","cited_by_count":73},{"id":"2011.11819","title":"When Machine Learning Meets Privacy: A Survey and Outlook","created":"2020-11-24","cited_by_count":68},{"id":"2304.06632","title":"AI-Generated Content (AIGC): A Survey","created":"2023-03-26","cited_by_count":59},{"id":"1802.06338","title":"Sequence-to-Sequence Prediction of Vehicle Trajectory via LSTM Encoder-Decoder Architecture","created":"2018-02-18","cited_by_count":55},{"id":"2311.13160","title":"Large Language Models in Education: Vision and Opportunities","created":"2023-11-22","cited_by_count":54},{"id":"2105.07878","title":"A Review on Explainability in Multimodal Deep Neural Nets","created":"2021-05-17","cited_by_count":46},{"id":"2302.05729","title":"A Brief Report on LawGPT 1.0: A Virtual Legal Assistant Based on GPT-3","created":"2023-02-11","cited_by_count":46},{"id":"2211.15914","title":"Prompted Opinion Summarization with GPT-3.5","created":"2022-11-29","cited_by_count":44},{"id":"1612.08321","title":"Generalized Optimal Matching Methods for Causal Inference","created":"2016-12-26","cited_by_count":39},{"id":"1805.09461","title":"Deep Reinforcement Learning For Sequence to Sequence Models","created":"2018-05-24","cited_by_count":39},{"id":"2111.08687","title":"INTERN: A New Learning Paradigm Towards General Vision","created":"2021-11-16","cited_by_count":33},{"id":"2205.13891","title":"Transformers from an Optimization Perspective","created":"2022-05-27","cited_by_count":27},{"id":"2311.05804","title":"Model-as-a-Service (MaaS): A Survey","created":"2023-11-10","cited_by_count":25},{"id":"1904.09020","title":"Genie: A Generator of Natural Language Semantic Parsers for Virtual Assistant Commands","created":"2019-04-18","cited_by_count":19},{"id":"2008.02063","title":"Compact Graph Architecture for Speech Emotion Recognition","created":"2020-08-05","cited_by_count":9},{"id":"2211.15588","title":"Internet of Behaviors: A Survey","created":"2022-11-28","cited_by_count":7},{"id":"1505.05899","title":"The IBM 2015 English Conversational Telephone Speech Recognition System","created":"2015-05-21","cited_by_count":6}],"next_cursor":null}