{"list":"other","total":53,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2303.11366","title":"Reflexion: Language Agents with Verbal Reinforcement Learning","created":"2023-03-20","cited_by_count":4276},{"id":"2308.11432","title":"A Survey on Large Language Model based Autonomous Agents","created":"2023-08-22","cited_by_count":2242},{"id":"2308.08155","title":"AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation","created":"2023-08-16","cited_by_count":1988},{"id":"2309.07864","title":"The Rise and Potential of Large Language Model Based Agents: A Survey","created":"2023-09-14","cited_by_count":1439},{"id":"2303.17580","title":"HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face","created":"2023-03-30","cited_by_count":1190},{"id":"1710.03740","title":"Mixed Precision Training","created":"2017-10-10","cited_by_count":1156},{"id":"2304.05128","title":"Teaching Large Language Models to Self-Debug","created":"2023-04-11","cited_by_count":988},{"id":"2305.02301","title":"Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes","created":"2023-05-03","cited_by_count":737},{"id":"2303.04671","title":"Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models","created":"2023-03-08","cited_by_count":668},{"id":"2104.10350","title":"Carbon Emissions and Large Neural Network Training","created":"2021-04-21","cited_by_count":567},{"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":"2207.04429","title":"LM-Nav: Robotic Navigation with Large Pre-Trained Models of Language, Vision, and Action","created":"2022-07-10","cited_by_count":439},{"id":"2309.05922","title":"A Survey of Hallucination in Large Foundation Models","created":"2023-09-12","cited_by_count":368},{"id":"2205.05198","title":"Reducing Activation Recomputation in Large Transformer Models","created":"2022-05-10","cited_by_count":302},{"id":"1802.05668","title":"Model compression via distillation and quantization","created":"2018-02-15","cited_by_count":289},{"id":"2305.15021","title":"EmbodiedGPT: Vision-Language Pre-Training via Embodied Chain of Thought","created":"2023-05-24","cited_by_count":279},{"id":"2308.07633","title":"A Survey on Model Compression for Large Language Models","created":"2023-08-15","cited_by_count":269},{"id":"2211.02001","title":"Estimating the Carbon Footprint of BLOOM, a 176B Parameter Language Model","created":"2022-11-03","cited_by_count":265},{"id":"2304.12995","title":"AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head","created":"2023-04-25","cited_by_count":265},{"id":"2305.04790","title":"MultiModal-GPT: A Vision and Language Model for Dialogue with Humans","created":"2023-05-08","cited_by_count":255},{"id":"2111.00364","title":"Sustainable AI: Environmental Implications, Challenges and Opportunities","created":"2021-10-30","cited_by_count":242},{"id":"1909.12326","title":"Model Pruning Enables Efficient Federated Learning on Edge Devices","created":"2019-09-26","cited_by_count":222},{"id":"2207.00112","title":"Language model compression with weighted low-rank factorization","created":"2022-06-30","cited_by_count":195},{"id":"2210.08964","title":"PromptCast: A New Prompt-based Learning Paradigm for Time Series Forecasting","created":"2022-09-20","cited_by_count":172},{"id":"2307.00691","title":"From ChatGPT to ThreatGPT: Impact of Generative AI in Cybersecurity and Privacy","created":"2023-07-03","cited_by_count":143},{"id":"2308.08469","title":"LLM4TS: Aligning Pre-Trained LLMs as Data-Efficient Time-Series Forecasters","created":"2023-08-16","cited_by_count":129},{"id":"2205.02302","title":"Machine Learning Operations (MLOps): Overview, Definition, and Architecture","created":"2022-05-04","cited_by_count":128},{"id":"2105.13120","title":"Sequence Parallelism: Long Sequence Training from System Perspective","created":"2021-05-26","cited_by_count":126},{"id":"2206.05229","title":"Measuring the Carbon Intensity of AI in Cloud Instances","created":"2022-06-10","cited_by_count":111},{"id":"2310.10196","title":"Large Models for Time Series and Spatio-Temporal Data: A Survey and Outlook","created":"2023-10-16","cited_by_count":110},{"id":"2110.14883","title":"Colossal-AI: A Unified Deep Learning System For Large-Scale Parallel Training","created":"2021-10-28","cited_by_count":96},{"id":"1812.02858","title":"Wireless Network Intelligence at the Edge","created":"2018-12-07","cited_by_count":92},{"id":"1909.00560","title":"Edge Intelligence: The Confluence of Edge Computing and Artificial Intelligence","created":"2019-09-02","cited_by_count":76},{"id":"2304.14979","title":"MLCopilot: Unleashing the Power of Large Language Models in Solving Machine Learning Tasks","created":"2023-04-28","cited_by_count":66},{"id":"2307.02779","title":"Large Language Models Empowered Autonomous Edge AI for Connected Intelligence","created":"2023-07-06","cited_by_count":56},{"id":"2306.10249","title":"Large Generative AI Models for Telecom: The Next Big Thing?","created":"2023-06-17","cited_by_count":52},{"id":"2202.06471","title":"Semantic Communication Meets Edge Intelligence","created":"2022-02-14","cited_by_count":21},{"id":"2311.05842","title":"AI-native Interconnect Framework for Integration of Large Language Model Technologies in 6G Systems","created":"2023-11-10","cited_by_count":19},{"id":"2311.16442","title":"Fast and Efficient 2-bit LLM Inference on GPU: 2/4/16-bit in a Weight Matrix with Asynchronous Dequantization","created":"2023-11-28","cited_by_count":14},{"id":"2205.01423","title":"Autonomy and Intelligence in the Computing Continuum: Challenges, Enablers, and Future Directions for Orchestration","created":"2022-05-03","cited_by_count":12},{"id":"2306.17170","title":"An Overview on Generative AI at Scale with Edge-Cloud Computing","created":"2023-06-02","cited_by_count":9},{"id":"2309.13315","title":"Semantic Communications using Foundation Models: Design Approaches and Open Issues","created":"2023-09-23","cited_by_count":9},{"id":"2309.02058","title":"How Can AI be Distributed in the Computing Continuum? Introducing the Neural Pub/Sub Paradigm","created":"2023-09-05","cited_by_count":4},{"id":"2312.03549","title":"Holmes: Towards Distributed Training Across Clusters with Heterogeneous NIC Environment","created":"2023-12-06","cited_by_count":4},{"id":"2308.02448","title":"From Military to Healthcare: Adopting and Expanding Ethical Principles for Generative Artificial Intelligence","created":"2023-08-04","cited_by_count":3},{"id":"1704.00411","title":"A Survey of Distributed Message Broker Queues","created":"2017-04-03","cited_by_count":1},{"id":"1902.07022","title":"Towards a Scaled IoT Pub/Sub Architecture for 5G Networks: the Case of Multiaccess Edge Computing","created":"2019-02-19","cited_by_count":1}],"next_cursor":null}