研究人员开发了一个多保真代理建模框架，用于预测集装箱船的风载荷，结合了经验数据和CFD模拟，以提高准确性和降低计算成本。另一篇论文介绍了一种使用闭式对数几率聚合器的先验无关鲁棒预测聚合方法，实现了接近最优的最小最大遗憾保证。此外，还提出了一个用于邻域聚合深度学习的新理论框架，为卷积神经网络提供了数学解释。最后，提出了一个名为Doloris的生成框架，用于非配对单细胞扰动估计，利用双扩散模型和稀疏性掩码策略来捕捉复杂的生物数据。 AI
影响 多保真建模、鲁棒预测、理论深度学习框架和单细胞数据分析方面的进步为AI从业者提供了新工具和见解。
排序理由 该集群包含多篇详细介绍机器学习及相关领域新研究的学术论文。
AI 生成摘要 · Google Gemini · 来自 10 个来源。 我们如何撰写摘要 →
完整方法见我们的编辑标准。
arXiv:2604.24672v1 Announce Type: new Abstract: We provide a mathematical interpretation of convolutional (or message passing) neural networks by using presheaves and copresheaves of the set of continuous functions over a topological space. Based on this interpretation, we formul…
arXiv:2604.22882v1 Announce Type: new Abstract: Modern container ships face higher wind loads due to increased windage areas, making accurate predictions of wind loads essential for mooring design. Existing empirical models, largely developed for container ships with smaller wind…
arXiv:2506.21107v3 Announce Type: replace Abstract: Estimating single-cell responses across various perturbations facilitates the identification of key genes and enhances drug screening, significantly boosting experimental efficiency. However, single-cell sequencing is a destruct…
arXiv:2604.24517v1 Announce Type: new Abstract: Robust forecast aggregation combines the predictions of multiple information sources to perform well in the worst case across all possible information structures. Previous work largely focuses on settings with a known binary state s…
We provide a mathematical interpretation of convolutional (or message passing) neural networks by using presheaves and copresheaves of the set of continuous functions over a topological space. Based on this interpretation, we formulate a theoretical heuristic which elaborates a n…
Robust forecast aggregation combines the predictions of multiple information sources to perform well in the worst case across all possible information structures. Previous work largely focuses on settings with a known binary state space, where the state is either 0 or 1. We study…
arXiv:2604.22464v1 Announce Type: new Abstract: Continual Model Merging (CMM) sequentially integrates task-specific models into a unified architecture without intensive retraining. However, existing CMM methods are hindered by a fundamental saturation-redundancy dilemma: backbone…
Continual Model Merging (CMM) sequentially integrates task-specific models into a unified architecture without intensive retraining. However, existing CMM methods are hindered by a fundamental saturation-redundancy dilemma: backbone-centric approaches face parameter saturation an…
arXiv:2604.23800v1 Announce Type: cross Abstract: Causal representation learning aims to recover the latent causal variables and their causal relations, typically represented by directed acyclic graphs (DAGs), from low-level observations such as image pixels. A prevailing line of…
Causal representation learning aims to recover the latent causal variables and their causal relations, typically represented by directed acyclic graphs (DAGs), from low-level observations such as image pixels. A prevailing line of research exploits multiple environments, which as…