两篇新研究论文探讨了改进基础模型不确定性量化方法。第一篇论文介绍了奇异值集成（SVE），一种参数高效的技术，通过调制权重矩阵的奇异值来创建多样化的模型集成，显著降低计算成本，同时保持准确性并提高校准度。第二篇论文实证比较了表格基础模型（特别是TabPFN）与高斯过程的性能，结果表明，虽然TabPFN在复杂、数据丰富的场景中表现出色，但在数据稀疏的环境中，高斯过程提供了更优越的性能和不确定性量化，尤其是在其核函数与底层函数良好匹配时。 AI
影响 不确定性量化的进步对于在安全关键型应用中部署基础模型至关重要，有望提高信任度和采用率。
排序理由 两篇在arXiv上发表的学术论文，提出了不确定性量化基础模型的新方法和比较研究。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
完整方法见我们的编辑标准。
arXiv:2601.22068v2 Announce Type: replace Abstract: Foundation models have become a dominant paradigm in machine learning, achieving remarkable performance across diverse tasks through large-scale pretraining. However, they often yield overconfident, uncalibrated predictions. The…
arXiv:2606.01427v1 Announce Type: new Abstract: Foundation models (FMs) have achieved substantial success in generalizing across tasks without problemspecific training or fine-tuning. However, many critical applications in mechanics and computational science require not only accu…
Foundation models (FMs) have achieved substantial success in generalizing across tasks without problemspecific training or fine-tuning. However, many critical applications in mechanics and computational science require not only accurate predictions but also reliable uncertainty q…