{"list":"other","total":78,"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"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":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"1910.13461","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","created":"2019-10-29","cited_by_count":5893},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"1907.05600","title":"Generative Modeling by Estimating Gradients of the Data Distribution","created":"2019-07-12","cited_by_count":4101},{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"id":"1909.11942","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","created":"2019-09-26","cited_by_count":2790},{"id":"1809.11096","title":"Large Scale GAN Training for High Fidelity Natural Image Synthesis","created":"2018-09-28","cited_by_count":2626},{"id":"2303.12712","title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","created":"2023-03-22","cited_by_count":2592},{"id":"2010.11934","title":"mT5: A massively multilingual pre-trained text-to-text transformer","created":"2020-10-22","cited_by_count":1818},{"id":"2210.02303","title":"Imagen Video: High Definition Video Generation with Diffusion Models","created":"2022-10-05","cited_by_count":1778},{"id":"1609.03499","title":"WaveNet: A Generative Model for Raw Audio","created":"2016-09-12","cited_by_count":1722},{"id":"1904.08779","title":"SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition","created":"2019-04-18","cited_by_count":1380},{"id":"2209.04747","title":"Diffusion Models in Vision: A Survey","created":"2022-09-10","cited_by_count":1015},{"id":"1606.05328","title":"Conditional Image Generation with PixelCNN Decoders","created":"2016-06-16","cited_by_count":862},{"id":"1605.05396","title":"Generative Adversarial Text to Image Synthesis","created":"2016-05-17","cited_by_count":735},{"id":"2203.17003","title":"Equivariant Diffusion for Molecule Generation in 3D","created":"2022-03-31","cited_by_count":677},{"id":"1711.10485","title":"AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks","created":"2017-11-28","cited_by_count":664},{"id":"2302.11382","title":"A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT","created":"2023-02-21","cited_by_count":619},{"id":"1612.03242","title":"StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks","created":"2016-12-10","cited_by_count":577},{"id":"1701.05517","title":"PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modifications","created":"2017-01-19","cited_by_count":417},{"id":"1905.07088","title":"Sliced Score Matching: A Scalable Approach to Density and Score Estimation","created":"2019-05-17","cited_by_count":384},{"id":"2302.09419","title":"A Comprehensive Survey on Pretrained Foundation Models: A History from BERT to ChatGPT","created":"2023-02-18","cited_by_count":368},{"id":"2101.05278","title":"GAN Inversion: A Survey","created":"2021-01-14","cited_by_count":367},{"id":"1905.02450","title":"MASS: Masked Sequence to Sequence Pre-training for Language Generation","created":"2019-05-07","cited_by_count":347},{"id":"2301.13867","title":"Mathematical Capabilities of ChatGPT","created":"2023-01-31","cited_by_count":268},{"id":"2303.07909","title":"Text-to-image Diffusion Models in Generative AI: A Survey","created":"2023-03-14","cited_by_count":265},{"id":"2303.10420","title":"A Comprehensive Capability Analysis of GPT-3 and GPT-3.5 Series Models","created":"2023-03-18","cited_by_count":246},{"id":"2203.09481","title":"Diffusion Probabilistic Modeling for Video Generation","created":"2022-03-16","cited_by_count":238},{"id":"2001.04063","title":"ProphetNet: Predicting Future N-gram for Sequence-to-Sequence Pre-training","created":"2020-01-13","cited_by_count":222},{"id":"1810.04020","title":"A Comprehensive Survey of Deep Learning for Image Captioning","created":"2018-10-06","cited_by_count":214},{"id":"2203.09516","title":"AutoSDF: Shape Priors for 3D Completion, Reconstruction and Generation","created":"2022-03-17","cited_by_count":208},{"id":"2302.01329","title":"Dreamix: Video Diffusion Models are General Video Editors","created":"2023-02-02","cited_by_count":191},{"id":"2301.01768","title":"The political ideology of conversational AI: Converging evidence on ChatGPT's pro-environmental, left-libertarian orientation","created":"2023-01-05","cited_by_count":189},{"id":"2303.10130","title":"GPTs are GPTs: An Early Look at the Labor Market Impact Potential of Large Language Models","created":"2023-03-17","cited_by_count":176},{"id":"2302.03494","title":"A Categorical Archive of ChatGPT Failures","created":"2023-02-06","cited_by_count":168},{"id":"1904.08067","title":"Text Classification Algorithms: A Survey","created":"2019-04-17","cited_by_count":163},{"id":"2004.14546","title":"WT5?! Training Text-to-Text Models to Explain their Predictions","created":"2020-04-30","cited_by_count":148},{"id":"2111.01690","title":"Recent Advances in End-to-End Automatic Speech Recognition","created":"2021-11-02","cited_by_count":140},{"id":"1511.02793","title":"Generating Images from Captions with Attention","created":"2015-11-09","cited_by_count":136},{"id":"1508.06615","title":"Character-Aware Neural Language Models","created":"2015-08-26","cited_by_count":132},{"id":"1609.06647","title":"Show and Tell: Lessons learned from the 2015 MSCOCO Image Captioning Challenge","created":"2016-09-21","cited_by_count":116},{"id":"2005.10433","title":"Text-to-Text Pre-Training for Data-to-Text Tasks","created":"2020-05-21","cited_by_count":104},{"id":"1605.02226","title":"Neural Autoregressive Distribution Estimation","created":"2016-05-07","cited_by_count":95},{"id":"2301.04655","title":"ChatGPT is not all you need. A State of the Art Review of large Generative AI models","created":"2023-01-11","cited_by_count":86},{"id":"2301.12959","title":"GALIP: Generative Adversarial CLIPs for Text-to-Image Synthesis","created":"2023-01-30","cited_by_count":85},{"id":"1611.01646","title":"Boosting Image Captioning with Attributes","created":"2016-11-05","cited_by_count":76},{"id":"2303.13336","title":"A Survey on Audio Diffusion Models: Text To Speech Synthesis and Enhancement in Generative AI","created":"2023-03-23","cited_by_count":68},{"id":"1306.0186","title":"RNADE: The real-valued neural autoregressive density-estimator","created":"2013-06-02","cited_by_count":66},{"id":"2303.07839","title":"ChatGPT Prompt Patterns for Improving Code Quality, Refactoring, Requirements Elicitation, and Software Design","created":"2023-03-11","cited_by_count":66},{"id":"2203.16262","title":"How Does SimSiam Avoid Collapse Without Negative Samples? A Unified Understanding with Self-supervised Contrastive Learning","created":"2022-03-30","cited_by_count":65},{"id":"2208.00173","title":"A Survey on Masked Autoencoder for Self-supervised Learning in Vision and Beyond","created":"2022-07-30","cited_by_count":58},{"id":"2011.06801","title":"A Comprehensive Survey on Deep Music Generation: Multi-level Representations, Algorithms, Evaluations, and Future Directions","created":"2020-11-13","cited_by_count":56},{"id":"2302.03495","title":"Can ChatGPT Write a Good Boolean Query for Systematic Review Literature Search?","created":"2023-02-03","cited_by_count":54},{"id":"2203.17248","title":"Dual Temperature Helps Contrastive Learning Without Many Negative Samples: Towards Understanding and Simplifying MoCo","created":"2022-03-30","cited_by_count":52},{"id":"2204.02492","title":"Towards End-to-end Unsupervised Speech Recognition","created":"2022-04-05","cited_by_count":45},{"id":"2302.04335","title":"Will ChatGPT get you caught? Rethinking of Plagiarism Detection","created":"2023-02-08","cited_by_count":41},{"id":"1803.05030","title":"Deep-FSMN for Large Vocabulary Continuous Speech Recognition","created":"2018-03-04","cited_by_count":28},{"id":"2212.09993","title":"Are Deep Neural Networks SMARTer than Second Graders?","created":"2022-12-20","cited_by_count":24},{"id":"2207.10899","title":"Decoupled Adversarial Contrastive Learning for Self-supervised Adversarial Robustness","created":"2022-07-22","cited_by_count":20},{"id":"2302.02805","title":"Investigating the use of ChatGPT for the scheduling of construction projects","created":"2023-01-27","cited_by_count":17},{"id":"2212.06933","title":"Paraphrase Identification with Deep Learning: A Review of Datasets and Methods","created":"2022-12-13","cited_by_count":13},{"id":"2212.11126","title":"Chatbots in a Botnet World","created":"2022-12-18","cited_by_count":8},{"id":"2301.13382","title":"Numeracy from Literacy: Data Science as an Emergent Skill from Large Language Models","created":"2023-01-31","cited_by_count":8},{"id":"1606.01700","title":"Gated Word-Character Recurrent Language Model","created":"2016-06-06","cited_by_count":5},{"id":"1704.02813","title":"Character-Word LSTM Language Models","created":"2017-04-10","cited_by_count":5}],"next_cursor":null}