NeurIPS

Flatness and Gradient Alignment Are Both Necessary: Spectral-Aware Gradient-Aligned Exploration for Multi-Distribution Learning

平坦性与梯度对齐都是必要的：面向多分布学习的频谱感知梯度对齐探索

Aristotelis Ballas, Christos Diou

机构 * Department of Informatics and Telematics（信息与电信系） 纠错

AI总结 本文提出SAGE方法，通过同时考虑损失景观的平坦性和梯度对齐性，改进多分布学习的泛化性能，实验表明其在DomainBed上达到新水平。

Comments Preprint - Submitted to NeurIPS 2026

A Space-Time Transformer for Precipitation Nowcasting

一种用于降水现在预测的空间-时间转换器

Levi Harris, Tianlong Chen

机构 * UNC Chapel Hill（北卡罗来纳大学教堂山分校） 纠错

AI总结 本文提出SaTformer，一种基于空间-时间注意力的视频转换器，用于从卫星辐射预测极端降水，并在NeurIPS Weather4Cast 2025挑战中取得第一名。

Comments NeurIPS Weather4Cast Challenge 2025

Efficiency, Feasibility, and Incentive-Awareness in Constrained Online Resource Allocation

受限在线资源分配中的效率、可行性和激励意识

Yan Dai, Negin Golrezaei, Patrick Jaillet

AI总结 研究长期约束下不可分割资源给策略性主体的动态分配，提出激励感知原始对偶框架，整合组件抑制操纵，设计新算法克服障碍，实现$\tilde{\mathcal O}(\sqrt T)$社会福利遗憾，满足约束并诱导近似真实均衡，还能推广到多单位多需求问题。

Comments A preliminary version was accepted to NeurIPS 2025. This version includes extension to multi-unit resource allocation, expanded numerical simulation, extensively refind technical exposition, and enhanced literature review and positioning