{"list":"other","total":79,"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":"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":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"1301.3781","title":"Efficient Estimation of Word Representations in Vector Space","created":"2013-01-16","cited_by_count":4375},{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"id":"1310.4546","title":"Distributed Representations of Words and Phrases and their Compositionality","created":"2013-10-16","cited_by_count":3474},{"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":"2209.14988","title":"DreamFusion: Text-to-3D using 2D Diffusion","created":"2022-09-29","cited_by_count":3025},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"id":"2107.13586","title":"Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing","created":"2021-07-28","cited_by_count":2234},{"id":"2012.07805","title":"Extracting Training Data from Large Language Models","created":"2020-12-14","cited_by_count":2189},{"id":"2303.03378","title":"PaLM-E: An Embodied Multimodal Language Model","created":"2023-03-06","cited_by_count":2071},{"id":"2203.07814","title":"Competition-Level Code Generation with AlphaCode","created":"2022-02-08","cited_by_count":1462},{"id":"2211.10440","title":"Magic3D: High-Resolution Text-to-3D Content Creation","created":"2022-11-18","cited_by_count":1290},{"id":"2201.08239","title":"LaMDA: Language Models for Dialog Applications","created":"2022-01-20","cited_by_count":1220},{"id":"2107.00630","title":"Variational Diffusion Models","created":"2021-07-01","cited_by_count":1153},{"id":"2209.14916","title":"Human Motion Diffusion Model","created":"2022-09-29","cited_by_count":1080},{"id":"1608.07187","title":"Semantics derived automatically from language corpora contain human-like biases","created":"2016-08-25","cited_by_count":901},{"id":"2301.10226","title":"A Watermark for Large Language Models","created":"2023-01-24","cited_by_count":725},{"id":"2110.04627","title":"Vector-quantized Image Modeling with Improved VQGAN","created":"2021-10-09","cited_by_count":658},{"id":"2301.00704","title":"Muse: Text-To-Image Generation via Masked Generative Transformers","created":"2023-01-02","cited_by_count":648},{"id":"2303.13375","title":"Capabilities of GPT-4 on Medical Challenge Problems","created":"2023-03-20","cited_by_count":638},{"id":"2104.04473","title":"Efficient Large-Scale Language Model Training on GPU Clusters Using Megatron-LM","created":"2021-04-09","cited_by_count":632},{"id":"2209.03143","title":"AudioLM: a Language Modeling Approach to Audio Generation","created":"2022-09-07","cited_by_count":616},{"id":"2212.10403","title":"Towards Reasoning in Large Language Models: A Survey","created":"2022-12-20","cited_by_count":596},{"id":"2302.14045","title":"Language Is Not All You Need: Aligning Perception with Language Models","created":"2023-02-27","cited_by_count":543},{"id":"2005.00341","title":"Jukebox: A Generative Model for Music","created":"2020-04-30","cited_by_count":542},{"id":"2210.10341","title":"BioGPT: Generative Pre-trained Transformer for Biomedical Text Generation and Mining","created":"2022-10-19","cited_by_count":538},{"id":"2210.02399","title":"Phenaki: Variable Length Video Generation From Open Domain Textual Description","created":"2022-10-05","cited_by_count":484},{"id":"2301.07597","title":"How Close is ChatGPT to Human Experts? Comparison Corpus, Evaluation, and Detection","created":"2023-01-18","cited_by_count":481},{"id":"2207.00032","title":"DeepSpeed Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scale","created":"2022-06-30","cited_by_count":407},{"id":"2303.11156","title":"Can AI-Generated Text be Reliably Detected?","created":"2023-03-17","cited_by_count":386},{"id":"2305.17333","title":"Fine-Tuning Language Models with Just Forward Passes","created":"2023-05-27","cited_by_count":345},{"id":"1709.10190","title":"Unified Deep Supervised Domain Adaptation and Generalization","created":"2017-09-28","cited_by_count":323},{"id":"2203.11147","title":"Teaching language models to support answers with verified quotes","created":"2022-03-21","cited_by_count":292},{"id":"2305.15005","title":"Sentiment Analysis in the Era of Large Language Models: A Reality Check","created":"2023-05-24","cited_by_count":268},{"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":"2102.10407","title":"VisualGPT: Data-efficient Adaptation of Pretrained Language Models for Image Captioning","created":"2021-02-20","cited_by_count":191},{"id":"2103.11790","title":"Large Pre-trained Language Models Contain Human-like Biases of What is Right and Wrong to Do","created":"2021-03-08","cited_by_count":178},{"id":"2212.03551","title":"Talking About Large Language Models","created":"2022-12-07","cited_by_count":175},{"id":"2302.03494","title":"A Categorical Archive of ChatGPT Failures","created":"2023-02-06","cited_by_count":168},{"id":"2302.07736","title":"Is ChatGPT better than Human Annotators? Potential and Limitations of ChatGPT in Explaining Implicit Hate Speech","created":"2023-02-11","cited_by_count":166},{"id":"2302.10198","title":"Can ChatGPT Understand Too? A Comparative Study on ChatGPT and Fine-tuned BERT","created":"2023-02-19","cited_by_count":155},{"id":"2208.12266","title":"Decoding speech perception from non-invasive brain recordings","created":"2022-08-25","cited_by_count":130},{"id":"2304.07619","title":"Can ChatGPT Forecast Stock Price Movements? Return Predictability and Large Language Models","created":"2023-04-15","cited_by_count":129},{"id":"2302.08081","title":"Exploring the Limits of ChatGPT for Query or Aspect-based Text Summarization","created":"2023-02-16","cited_by_count":122},{"id":"2304.09667","title":"GeneGPT: Augmenting Large Language Models with Domain Tools for Improved Access to Biomedical Information","created":"2023-04-19","cited_by_count":117},{"id":"2305.13292","title":"VideoLLM: Modeling Video Sequence with Large Language Models","created":"2023-05-22","cited_by_count":116},{"id":"1907.05774","title":"Hello, It's GPT-2 -- How Can I Help You? Towards the Use of Pretrained Language Models for Task-Oriented Dialogue Systems","created":"2019-07-12","cited_by_count":110},{"id":"2212.09292","title":"ChatGPT: The End of Online Exam Integrity?","created":"2022-12-19","cited_by_count":88},{"id":"2208.11663","title":"PEER: A Collaborative Language Model","created":"2022-08-24","cited_by_count":86},{"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":"2301.13852","title":"ChatGPT or Human? Detect and Explain. Explaining Decisions of Machine Learning Model for Detecting Short ChatGPT-generated Text","created":"2023-01-30","cited_by_count":85},{"id":"2303.11717","title":"A Complete Survey on Generative AI (AIGC): Is ChatGPT from GPT-4 to GPT-5 All You Need?","created":"2023-03-21","cited_by_count":84},{"id":"2106.00085","title":"Language Model Evaluation Beyond Perplexity","created":"2021-05-31","cited_by_count":78},{"id":"2209.00731","title":"In conversation with Artificial Intelligence: aligning language models with human values","created":"2022-09-01","cited_by_count":62},{"id":"2301.11796","title":"Call for Papers -- The BabyLM Challenge: Sample-efficient pretraining on a developmentally plausible corpus","created":"2023-01-27","cited_by_count":62},{"id":"2304.06488","title":"One Small Step for Generative AI, One Giant Leap for AGI: A Complete Survey on ChatGPT in AIGC Era","created":"2023-04-04","cited_by_count":55},{"id":"2302.06466","title":"ChatGPT versus Traditional Question Answering for Knowledge Graphs: Current Status and Future Directions Towards Knowledge Graph Chatbots","created":"2023-02-08","cited_by_count":47},{"id":"2206.00169","title":"Discovering the Hidden Vocabulary of DALLE-2","created":"2022-06-01","cited_by_count":43},{"id":"2303.09038","title":"Translating Radiology Reports into Plain Language using ChatGPT and GPT-4 with Prompt Learning: Promising Results, Limitations, and Potential","created":"2023-03-16","cited_by_count":39},{"id":"2105.11108","title":"Pre-trained Language Model based Ranking in Baidu Search","created":"2021-05-24","cited_by_count":34},{"id":"2305.12477","title":"GPT-3.5, GPT-4, or BARD? Evaluating LLMs Reasoning Ability in Zero-Shot Setting and Performance Boosting Through Prompts","created":"2023-05-21","cited_by_count":34},{"id":"2305.03123","title":"ChatGPT Needs SPADE (Sustainability, PrivAcy, Digital divide, and Ethics) Evaluation: A Review","created":"2023-04-13","cited_by_count":28},{"id":"2302.06474","title":"Applying BERT and ChatGPT for Sentiment Analysis of Lyme Disease in Scientific Literature","created":"2023-02-07","cited_by_count":26},{"id":"2302.13817","title":"Let's have a chat! A Conversation with ChatGPT: Technology, Applications, and Limitations","created":"2023-02-27","cited_by_count":16},{"id":"2302.09051","title":"Complex QA and language models hybrid architectures, Survey","created":"2023-02-17","cited_by_count":14},{"id":"2303.01980","title":"Towards energy-efficient Deep Learning: An overview of energy-efficient approaches along the Deep Learning Lifecycle","created":"2023-02-05","cited_by_count":14},{"id":"2304.02017","title":"Unlocking the Potential of ChatGPT: A Comprehensive Exploration of its Applications, Advantages, Limitations, and Future Directions in Natural Language Processing","created":"2023-03-27","cited_by_count":11},{"id":"2112.09726","title":"Soundify: Matching Sound Effects to Video","created":"2021-12-17","cited_by_count":6},{"id":"2303.03885","title":"AI Risk Skepticism, A Comprehensive Survey","created":"2023-02-16","cited_by_count":6},{"id":"2201.09049","title":"LTC-SUM: Lightweight Client-driven Personalized Video Summarization Framework Using 2D CNN","created":"2022-01-22","cited_by_count":4},{"id":"2102.10410","title":"NUBOT: Embedded Knowledge Graph With RASA Framework for Generating Semantic Intents Responses in Roman Urdu","created":"2021-02-20","cited_by_count":1}],"next_cursor":null}