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

2026-06-23 至 2026-06-23 共收录 7
2606.21973 2026-06-23 cs.LG cs.AI 新提交

SPOTR: Spatio-temporal Pooling One-Token Reconstruction for Universal Physiological Signal Self-supervised Learning

SPOTR: 面向通用生理信号自监督学习的时空池化单令牌重建

Yiyu Gui, Mingzhi Chen, Yuesheng Zhu, Guibo Luo, Yuchao Yang

机构 * New Cornerstone Science Laboratory, Guangdong Provincial Key Laboratory of In-Memory Computing Chips, Shenzhen Graduate School, Peking University(新基石科学实验室,广东省存算一体芯片重点实验室,北京大学深圳研究生院) Guangdong Provincial Key Laboratory of Ultra High Definition Immersive Media Technology, Shenzhen Graduate School, Peking University(广东省超高清沉浸式媒体技术重点实验室,北京大学深圳研究生院)

AI总结 提出SPOTR框架,通过单令牌全局瓶颈压缩-重建预训练,解决生理信号自监督学习在异构数据集上的性能瓶颈,在线性探测下显著提升AUC并降低计算开销。

Comments The paper has been accepted by IJCAI-ECAI 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.20817 2026-06-23 cs.NE cs.LG 新提交

Provably Sub-Linear Two-Timescale NeuroEvolution with Online Plasticity

具有在线可塑性的可证明次线性双时间尺度神经进化

Shishen Lin, Yixin Chen

机构 * Department of Statistics, University of Warwick(华威大学统计系) Biozentrum, University of Basel(巴塞尔大学生物中心)

AI总结 提出双时间尺度神经进化在线学习框架,外环搜索架构、内环通过奖励调制可塑性在线调整权重,证明次线性遗憾,在控制任务上优于纯NEAT且与强化学习基线竞争。

Comments 28 pages; Accepted at IJCAI-ECAI 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.13405 2026-06-23 cs.AI cs.MA 新提交

Neuro-Symbolic Agents for Regulated Process Automation: Challenges and Research Agenda

用于受规管流程自动化的神经符号代理:挑战与研究议程

Alexander Rombach, Chantale Lauer, Nijat Mehdiyev

机构 * German Research Center for Artificial Intelligence (DFKI)(德国人工智能研究中心(DFKI)) Saarland University(萨尔大学)

AI总结 提出将领域内符号结构(法规、流程模型、合规约束)作为代理核心架构组件,实现合规性内置(compliance-by-construction)以补充护栏监控,并列出神经符号研究挑战。

Comments Accepted as a poster in NILA Workshop @ IJCAI-ECAI 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.29245 2026-06-23 cs.CR cs.CL cs.LG 版本更新

Implicit Identity Technologies for LLMs: Fingerprinting and Watermarking across Datasets, Models, and Generated Content

LLM的隐式身份技术:跨数据集、模型和生成内容的指纹识别与水印

Bing Liu, Shunping Wang, Yufan Zhu, Xinyi Yu, Jing Huang, Linkang Du, Hongbin Pei, Wei Luo

机构 * School of Cyber Science and Engineering, Xi’an Jiaotong University, Xi’an, China(西安交通大学计算机科学与工程学院) State Grid Henan Marketing Service Center, Henan, China(国网河南营销服务中心) Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China(中国科学院信息工程研究所) School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China(中国科学院大学网络安全学院) School of Information Technology, Deakin University, Geelong, Australia(迪金大学信息技术学院)

AI总结 本文综述了LLM指纹识别和水印技术,提出隐式身份统一抽象,并基于生命周期分类法组织数据集、模型和生成内容的技术,建立评估框架。

Comments Accepted by IJCAI-ECAI 2026. 11 pages, 1 figure. Survey and taxonomy of LLM fingerprinting and watermarking for identity, provenance, generated-content attribution, and asset protection

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.12947 2026-06-23 cs.CV 版本更新

DivCon-NeRF: Diverse and Consistent Ray Augmentation for Few-Shot NeRF

DivCon-NeRF:用于少样本NeRF的多样且一致的射线增强

Ingyun Lee, Jae Won Jang, Seunghyeon Seo, Nojun Kwak

机构 * Seoul National University(首尔国立大学)

AI总结 针对少样本NeRF中稀疏视图导致的过拟合和伪影问题,提出基于球面的射线增强方法,通过一致性掩码过滤不一致射线,结合定制损失函数减少浮点伪影和视觉失真,在多个数据集上优于现有方法。

Comments Accepted to IJCAI 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.15378 2026-06-23 cs.CL 版本更新

AlgoSimBench: Identifying Algorithmically Similar Problems for Competitive Programming

AlgoSimBench: 识别算法相似问题的竞赛编程基准

Jierui Li, Raymond Mooney

机构 * The University of Texas at Austin(德克萨斯大学奥斯汀分校)

AI总结 提出AlgoSimBench基准,通过对抗性设计的多选题评估大语言模型识别算法相似问题的能力,并引入尝试解决方案匹配方法提升准确率。

Comments 14 pages, accepted to IJCAI 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2103.00180 2026-06-23 cs.NE cs.AI cs.LG

Incorporating Domain Knowledge into Deep Neural Networks

将领域知识纳入深度神经网络

Tirtharaj Dash, Sharad Chitlangia, Aditya Ahuja, Ashwin Srinivasan

机构 * APP Centre for Artificial Intelligence Research (APPCAIR)(人工智能研究中心) Department of Electrical and Electronics Engineering(电子与电气工程系) Department of Computer Science and Information Systems(计算机科学与信息系统系) BITS Pilani, K.K. Birla Goa Campus(比斯汉学院,戈亚校区)

AI总结 本文探讨了如何通过逻辑和数值约束将领域知识融入神经网络模型,分析了不同子类别的技术与成果,以提升机器学习在人机协作中的表现。

Comments Submitted to IJCAI-2021 Survey Track (6+2 pages)

Journal ref extended version published in: Scientific Reports 12, 1040 (2022)

详情

展开后加载摘要…

URL PDF HTML 收藏