LLM4Science最新趋势吴郦军微软研究院

Recent Trends in LLM4ScienceLijun Wu*Works done when in MSR AI4Science, now in ByteDanceYSSNLP2024YSSNLP2024YSSNLP2024YSSNLP2024YSSNLP2024YSSNLP2024Large Language ModelsLarge language models (LLMs) have shown great success!YSSNLP2024YSSNLP2024YSSNLP2024YSSNLP2024YSSNLP2024YSSNLP2024Scientific DiscoveryAlphaFold (1, 2, 3) (protein folding)GNoMe (material discovery)GraphCast/MetNet/Aurora (weather)YSSNLP2024YSSNLP2024YSSNLP2024YSSNLP2024YSSNLP2024YSSNLP2024Large language models (LLMs)Scientific discoveryLLMfor ScienceYSSNLP2024YSSNLP2024YSSNLP2024YSSNLP2024YSSNLP2024YSSNLP2024Outline1.LLM4Science Report (GPT-4)2.Multimodal Pretrained Scientific LLM3.FutureYSSNLP2024YSSNLP2024YSSNLP2024YSSNLP2024YSSNLP2024YSSNLP2024LLM4Science ReportThe Impact of Large Language Models on Scientific Discovery: a Preliminary Study using GPT-4MSR AI4Science, Microsoft Azure QuantumYSSNLP2024YSSNLP2024YSSNLP2024YSSNLP2024YSSNLP2024YSSNLP2024Understan-ding conceptsDrug-target bindingMolecular property predicti