一篇新论文挑战了在药物发现中大型人工智能模型总是更优越的假设。研究人员发现，在分子性质和活性预测任务上，经典的机器学习模型和图神经网络的性能常常优于更大、更通用的模型。虽然大型模型可能在零样本推理等领域提供优势，但其预测优势并非普遍适用，并且在很大程度上取决于特定的任务匹配度。 AI
影响 表明在某些药物发现预测任务中，专门化的、更小的模型可能比大型、通用的AI更有效。
排序理由 学术论文，评估模型在特定基准上的扩展性能。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2604.26498v1 Announce Type: new Abstract: The rapid growth of molecular foundation models and general-purpose large language models has encouraged a scale-centric view of artificial intelligence in drug discovery, in which larger pretrained models are expected to supersede …
The rapid growth of molecular foundation models and general-purpose large language models has encouraged a scale-centric view of artificial intelligence in drug discovery, in which larger pretrained models are expected to supersede compact cheminformatics models and task-specific…