arXivDaily arXiv每日学术速递 周一至周五更新

期刊&会议

International Joint Conference on Artificial Intelligence · 会议 · Artificial Intelligence

2026-05-14 至 2026-05-14 共收录 5
2605.13407 2026-05-14 cs.LG cs.CE q-fin.ST

Vector-Quantized Discrete Latent Factors Meet Financial Priors: Dynamic Cross-Sectional Stock Ranking Prediction for Portfolio Construction

向量量化离散潜在因子融合金融先验:动态横截面股票排名预测用于投资组合构建

Namhyoung Kim, Jae Wook Song

机构 * RiskX Hanyang University(翰阳大学)

AI总结 本文提出PRISM-VQ模型,结合专家先验因子和向量量化离散潜在因子,通过结构条件混合专家生成时间变化因子载荷,提升横截面股票收益预测和投资组合表现。

Comments IJCAI 2026 Accepted Paper including Technical Appendix

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.13332 2026-05-14 cs.AI cs.CC

Diversity of Extensions in Abstract Argumentation

抽象论证中扩展的多样性

Johannes K. Fichte, Markus Hecher, Yasir Mahmood, Zhengjun Wang

机构 * Department of Computer and Information Science (IDA), Linköping University, Sweden(链接öping大学计算机与信息科学系(IDA)) University of Potsdam, Germany & University of Artois, CNRS, UMR8188 (CRIL), France(波茨坦大学 & 阿尔托伊斯大学、法国CNRS UMR8188(CRIL)) Data Science Group, Heinz Nixdorf Institute, Paderborn University, Germany(帕德博恩大学数据科学小组、海因茨·尼克斯多夫研究所)

AI总结 研究了抽象论证中扩展多样性的量化概念,探讨了扩展的兼容性及计算最大多样性k值的方法。

Comments Technical Report to the paper accepted at IJCAI 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.13229 2026-05-14 cs.AI cs.SE

Improving Code Translation with Syntax-Guided and Semantic-aware Preference Optimization

通过语法引导和语义感知的偏好优化改进代码翻译

Yuhan Wu, Huan Zhang, Wei Cheng, Chen Shen, Jingyue Yang, Wei Hu

机构 * State Key Laboratory for Novel Software Technology, Nanjing University, China(南京大学新型软件技术国家重点实验室) National Institute of Healthcare Data Science, Nanjing University, China(南京大学健康数据科学国家研究院)

AI总结 本文提出CTO方法,通过对比学习训练跨语言语义模型,结合编译器反馈实现代码翻译的语法和语义优化,实验表明其在C++、Java和Python翻译中表现优异。

Comments Accepted in the 35th International Joint Conference on Artificial Intelligence (IJCAI 2016)

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.13153 2026-05-14 cs.AI

Strikingness-Aware Evaluation for Temporal Knowledge Graph Reasoning

面向时间知识图谱推理的显著性感知评估

Rikui Huang, Shengzhe Zhang, Wei Wei

机构 * School of Computer Science & Technology, Huazhong University of Science and Technology(华中科技大学计算机科学与技术学院) Institute of Artificial Intelligence, Huazhong University of Science and Technology(华中科技大学人工智能研究院) School of Artificial Intelligence & Automation, Huazhong University of Science and Technology(华中科技大学人工智能与自动化学院)

AI总结 本文提出显著性感知评估框架,通过引入基于规则的显著性测量框架量化事件显著性,改进时间知识图谱推理的评估方法,实验表明不同模型在不同显著性事件上的表现差异。

Comments Accepted to IJCAI-ECAI 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.12691 2026-05-14 cs.AI

On the Size Complexity and Decidability of First-Order Progression

关于一阶推进的大小复杂性与可判定性

Jens Classen, Daxin Liu

机构 * Department of People and Technology, Roskilde University, Denmark(罗斯基尔德大学人机技术系,丹麦) State Key Laboratory for Novel Software Technology, Nanjing University, China(南京大学新型软件技术国家重点实验室,中国)

AI总结 本文研究了一阶推进在局部效应、正常和无环动作类中的大小复杂性,证明其在合理假设下仅呈多项式增长,并展示在可判定片段中推进保持可判定性。

Comments This is an extended version of an identically-titled paper accepted for publication at IJCAI 2026. This version contains an appendix with further proofs

详情

展开后加载摘要…

URL PDF HTML 收藏