IJCAI

Quantifying Risk Under Evolving Uncertainty: Belief-Dependent Robustness for Safe Sequential Decision Making

演化不确定性下的风险量化：面向安全序贯决策的信念依赖鲁棒性

Deep Kumar Ganguly, Jan Kretinsky

机构 * Technical University of Munich（慕尼黑工业大学） ； Masaryk University（马萨里克大学） 纠错

AI总结 本文提出RATTL算法，将智能体谨慎程度与认知不确定性绑定，证明其规划问题适定且满足安全三明治性质，可保障LLM等智能体在不确定性下的运行时安全。

Comments Accepted for presentation at the IJCAI-ECAI 2026 RobustifAI workshop

Vision Transformers for End-to-End Quark-Gluon Jet Classification from Calorimeter Images

用于量能器图像中夸克-胶子喷注端到端分类的视觉Transformer

Md Abrar Jahin, Shahriar Soudeep, Arian Rahman Aditta, M. F. Mridha, Nafiz Fahad, Md. Jakir Hossen

机构 * University of Southern California American International University-Bangladesh Khulna University of Engineering \& Technology Multimedia University 纠错

AI总结 本研究以2012年CMS开放数据为基础，系统评估ViT及ViT-CNN混合模型，发现其在夸克-胶子喷注分类任务中优于CNN基线，建立了相关系统框架与基准。

Comments Accepted in Third International Workshop on Generalizing from Limited Resources in the Open World Workshop at International Joint Conference on Artificial Intelligence (IJCAI) 2025