{"list":"other","total":62,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"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":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2011.13456","title":"Score-Based Generative Modeling through Stochastic Differential Equations","created":"2020-11-26","cited_by_count":9122},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"1505.00468","title":"VQA: Visual Question Answering","created":"2015-05-03","cited_by_count":2506},{"id":"1311.2524","title":"Rich feature hierarchies for accurate object detection and semantic segmentation","created":"2013-11-11","cited_by_count":2162},{"id":"2108.01073","title":"SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations","created":"2021-08-02","cited_by_count":1937},{"id":"2104.07636","title":"Image Super-Resolution via Iterative Refinement","created":"2021-04-15","cited_by_count":1511},{"id":"2306.14824","title":"Kosmos-2: Grounding Multimodal Large Language Models to the World","created":"2023-06-26","cited_by_count":1089},{"id":"2212.11565","title":"Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation","created":"2022-12-22","cited_by_count":961},{"id":"2303.17564","title":"BloombergGPT: A Large Language Model for Finance","created":"2023-03-30","cited_by_count":939},{"id":"1606.05328","title":"Conditional Image Generation with PixelCNN Decoders","created":"2016-06-16","cited_by_count":862},{"id":"1912.02164","title":"Plug and Play Language Models: A Simple Approach to Controlled Text Generation","created":"2019-12-04","cited_by_count":799},{"id":"2309.05519","title":"NExT-GPT: Any-to-Any Multimodal LLM","created":"2023-09-11","cited_by_count":615},{"id":"1710.07035","title":"Generative Adversarial Networks: An Overview","created":"2017-10-19","cited_by_count":590},{"id":"2302.14045","title":"Language Is Not All You Need: Aligning Perception with Language Models","created":"2023-02-27","cited_by_count":543},{"id":"1905.05055","title":"Object Detection in 20 Years: A Survey","created":"2019-05-13","cited_by_count":531},{"id":"1807.05511","title":"Object Detection with Deep Learning: A Review","created":"2018-07-15","cited_by_count":528},{"id":"2111.02358","title":"VLMo: Unified Vision-Language Pre-Training with Mixture-of-Modality-Experts","created":"2021-11-03","cited_by_count":425},{"id":"2303.11156","title":"Can AI-Generated Text be Reliably Detected?","created":"2023-03-17","cited_by_count":386},{"id":"1606.01847","title":"Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding","created":"2016-06-06","cited_by_count":243},{"id":"2309.03905","title":"ImageBind-LLM: Multi-modality Instruction Tuning","created":"2023-09-07","cited_by_count":142},{"id":"1610.03483","title":"Learning in Implicit Generative Models","created":"2016-10-11","cited_by_count":125},{"id":"1607.05910","title":"Visual Question Answering: A Survey of Methods and Datasets","created":"2016-07-20","cited_by_count":123},{"id":"2105.10311","title":"Pretrained Language Models for Text Generation: A Survey","created":"2021-05-21","cited_by_count":95},{"id":"2304.06798","title":"On the Opportunities and Challenges of Foundation Models for Geospatial Artificial Intelligence","created":"2023-04-13","cited_by_count":88},{"id":"2307.00855","title":"Review of Large Vision Models and Visual Prompt Engineering","created":"2023-07-03","cited_by_count":77},{"id":"2305.01118","title":"CSP: Self-Supervised Contrastive Spatial Pre-Training for Geospatial-Visual Representations","created":"2023-05-01","cited_by_count":69},{"id":"1411.6447","title":"The Application of Two-level Attention Models in Deep Convolutional Neural Network for Fine-grained Image Classification","created":"2014-11-24","cited_by_count":67},{"id":"2007.12391","title":"Artificial Intelligence in the Creative Industries: A Review","created":"2020-07-24","cited_by_count":61},{"id":"1610.01465","title":"Visual Question Answering: Datasets, Algorithms, and Future Challenges","created":"2016-10-05","cited_by_count":56},{"id":"2303.15935","title":"When Brain-inspired AI Meets AGI","created":"2023-03-28","cited_by_count":54},{"id":"2310.10072","title":"Fine-tuning ChatGPT for Automatic Scoring","created":"2023-10-16","cited_by_count":51},{"id":"2306.08666","title":"Radiology-GPT: A Large Language Model for Radiology","created":"2023-06-14","cited_by_count":44},{"id":"2306.05480","title":"Artificial General Intelligence for Medical Imaging Analysis","created":"2023-06-08","cited_by_count":32},{"id":"2211.14228","title":"GPT-3-driven pedagogical agents for training children's curious question-asking skills","created":"2022-11-25","cited_by_count":29},{"id":"2305.03513","title":"ChatGraph: Interpretable Text Classification by Converting ChatGPT Knowledge to Graphs","created":"2023-05-03","cited_by_count":27},{"id":"2302.03900","title":"Zero-shot Generation of Coherent Storybook from Plain Text Story using Diffusion Models","created":"2023-02-08","cited_by_count":26},{"id":"2105.09392","title":"Geographic Question Answering: Challenges, Uniqueness, Classification, and Future Directions","created":"2021-05-19","cited_by_count":24},{"id":"2209.11830","title":"Multiple-Choice Question Generation: Towards an Automated Assessment Framework","created":"2022-09-23","cited_by_count":23},{"id":"2305.11033","title":"Visual Question Answering: A Survey on Techniques and Common Trends in Recent Literature","created":"2023-05-18","cited_by_count":21},{"id":"2306.11892","title":"Exploring New Frontiers in Agricultural NLP: Investigating the Potential of Large Language Models for Food Applications","created":"2023-06-20","cited_by_count":21},{"id":"2106.11485","title":"Spatial-Temporal Super-Resolution of Satellite Imagery via Conditional Pixel Synthesis","created":"2021-06-22","cited_by_count":20},{"id":"2309.10160","title":"RadOnc-GPT: A Large Language Model for Radiation Oncology","created":"2023-09-18","cited_by_count":18},{"id":"2308.06088","title":"Assessing Student Errors in Experimentation Using Artificial Intelligence and Large Language Models: A Comparative Study with Human Raters","created":"2023-08-11","cited_by_count":16},{"id":"2305.00201","title":"Instruction-ViT: Multi-Modal Prompts for Instruction Learning in ViT","created":"2023-04-29","cited_by_count":14},{"id":"2005.09525","title":"Toward Automated Classroom Observation: Multimodal Machine Learning to Estimate CLASS Positive Climate and Negative Climate","created":"2020-05-19","cited_by_count":8},{"id":"2304.04893","title":"EVKG: An Interlinked and Interoperable Electric Vehicle Knowledge Graph for Smart Transportation System","created":"2023-04-10","cited_by_count":6},{"id":"2110.03895","title":"ALL-IN-ONE: Multi-Task Learning BERT models for Evaluating Peer Assessments","created":"2021-10-08","cited_by_count":4},{"id":"2308.10454","title":"Elucidating STEM Concepts through Generative AI: A Multi-modal Exploration of Analogical Reasoning","created":"2023-08-21","cited_by_count":3},{"id":"2106.07556","title":"Long Term Object Detection and Tracking in Collaborative Learning Environments","created":"2021-06-02","cited_by_count":2},{"id":"2304.06270","title":"Gamifying Math Education using Object Detection","created":"2023-04-13","cited_by_count":2},{"id":"2310.00413","title":"SSIF: Learning Continuous Image Representation for Spatial-Spectral Super-Resolution","created":"2023-09-30","cited_by_count":2}],"next_cursor":null}