arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~

期刊&会议

International Joint Conference on Artificial Intelligence · 会议 · Artificial Intelligence

至 收录 2909
1807.03001 2026-06-04 cs.NE cs.SY eess.SY

Learning Functions in Large Networks requires Modularity and produces Multi-Agent Dynamics

在大规模网络中学习函数需要模块化并产生多智能体动态

C. H. Huck Yang, Rise Ooi, Tom Hiscock, Victor Eguiluz, Jesper Tegnér

AI总结 本文研究了生物网络中是否存在更大的动态网络模组,并通过梯度下降机器学习和遗传算法来学习这些模组,发现学习能力受限于稳定性约束,从而强调了模块化在网络系统中的重要性。

Comments Accepted at the Joint ICML and IJCAI Workshop on Computational Biology (ICML-IJCAI WCB) to be held in Stockholm SWEDEN, 2018. Referring to accepted-papers?authuser=0" target="_blank" rel="noopener">https://sites.google.com/view/wcb2018/accepted-papers?authuser=0 update the team-learning figure

URL PDF HTML 收藏
1703.05487 2026-06-04 math.NA cs.NA

Accelerated and Inexact Soft-Impute for Large-Scale Matrix and Tensor Completion

加速与近似软插值用于大规模矩阵和张量补全

Quanming Yao, James T. Kwok

AI总结 本文提出了一种加速的软插值算法,通过近似奇异值阈值化方案降低迭代复杂度,实现低秩矩阵和张量补全的快速收敛。

Comments Journal version of previous conference paper 'Accelerated inexact soft-impute for fast large-scale matrix completion' appeared at IJCAI 2015

URL PDF HTML 收藏
1705.08927 2026-06-04 quant-ph cs.AI cs.ET cs.SY eess.SY

Compiling quantum circuits to realistic hardware architectures using temporal planners

利用时间规划器将量子电路编译到现实硬件架构

Davide Venturelli, Minh Do, Eleanor Rieffel, Jeremy Frank

机构 * NASA Ames Research Center, Quantum Artificial Intelligence Laboratory(美国国家航空航天局阿姆斯研究中心,量子人工智能实验室) USRA Research Institute for Advanced Computer Science (RIACS)(美国宇航局高级计算机科学研究所(RIACS)) Stinger Ghaffarian Technologies (SGT Inc.)(Stinger Ghaffarian技术(SGT公司)) NASA Ames Research Center, Planning and Scheduling Group(美国国家航空航天局阿姆斯研究中心,计划与调度组)

AI总结 本文研究了将量子电路编译到新兴量子硬件的时空规划方法,重点探讨了超导架构的最近邻约束,并通过QAOA电路的实验验证了时间规划在编译优化中的可行性。

Comments updated manuscript, more planners and results

Journal ref 2017 Quantum Sci. Technol. - also related to proceedings of IJCAI 2017, and ICAPS SPARK Workshop 2017

URL PDF HTML 收藏
1704.07669 2026-06-04 cs.DS cs.LG cs.NA math.NA

Single-Pass PCA of Large High-Dimensional Data

大规模高维数据的单次PCA处理

Wenjian Yu, Yu Gu, Jian Li, Shenghua Liu, Yaohang Li

机构 * Department of Computer Science(计算机科学系) Tsinghua National Lab of Information Science and Technology(清华大学信息科学与技术国家实验室) Tsinghua University(清华大学) Institute for Interdisciplinary Information Sciences(交叉信息科学与工程研究院) Department of Electronic Engineering(电子工程系) Institute of Computing Technology(计算技术研究所) Chinese Academy of Sciences(中国科学院) Old Dominion University(老 Dominion 大学)

AI总结 本文提出一种单次随机算法实现大规模高维数据的PCA,适用于存储在慢速存储器或流式生成的数据,实验验证其准确性,比现有算法误差小多个数量级,可在24分钟内计算50个主成分。

Comments IJCAI 2017, 16 pages, 6 figures

URL PDF HTML 收藏
1605.09497 2026-06-04 cs.GT cs.AI cs.MA cs.SY eess.SY

Interdependent Scheduling Games

相互依赖的调度博弈

Andres Abeliuk, Haris Aziz, Gerardo Berbeglia, Serge Gaspers, Petr Kalina, Nicholas Mattei, Dominik Peters, Paul Stursberg, Pascal Van Hentenryck, Toby Walsh

AI总结 本文研究了相互依赖的调度博弈模型,探讨了在基础设施规划与协调中的应用,分析了福利最大化、纳什均衡的存在与计算等核心问题。

Comments Accepted to IJCAI 2016

URL PDF HTML 收藏
1502.05443 2026-06-04 cs.AI cs.SY eess.SY

Influence-Optimistic Local Values for Multiagent Planning --- Extended Version

多智能体规划中的影响乐观局部值---扩展版

Frans A. Oliehoek, Matthijs T. J. Spaan, Stefan Witwicki

AI总结 本文提出一种适用于非因子化价值函数的多智能体规划影响乐观上界方法,通过划分子问题并乐观假设系统影响,提供质量保证并改进启发式搜索效果。

Comments Long version of IJCAI 2015 paper (and extended abstract at AAMAS 2015)

URL PDF HTML 收藏
2606.01475 2026-06-02 cs.CY

An LLM-based Chain-of-Response Counter-Scam System

基于LLM的链式响应反诈骗系统

Heedou Kim, Mogan Gim, Donghee Choi, Hoonick Lee, Soonil Bae, Mi-Young Kim, Jaewoo Kang

AI总结 提出Counter Scam框架,利用LLM多智能体协同实现从检测到调查的端到端反诈骗响应,通过CSRA、CSRT和CSRD组件提升效率,实验表明微调sLLM在CSRT任务上超越商业模型10%以上。

Comments This paper has been accepted for publication at IJCAI 2026

URL PDF HTML 收藏
2606.01012 2026-06-02 cs.AI cond-mat.mtrl-sci

Property Prediction of Stacked Bilayer Materials: A Multimodal Learning Approach

堆叠双层材料的性质预测:一种多模态学习方法

An Vuong, Minh-Hao Van, Chen Zhao, Xintao Wu

机构 * University of Arkansas(亚拉巴马大学) Baylor University(贝勒大学)

AI总结 提出一种多模态学习方法,通过联合建模不同材料层间的界面,预测给定配置下垂直堆叠产生的性质,实验证明其有效性和高效性。

Comments Accepted to the 35th International Joint Conference on Artificial Intelligence (IJCAI 2026)

URL PDF HTML 收藏
2605.01797 2026-06-02 cs.AI

Neural Decision-Propagation for Answer Set Programming

面向回答集编程的神经决策传播

Thomas Eiter, Katsumi Inoue, Sota Moriyama

机构 * Vienna University of Technology (TU Wien)(维也纳技术大学( TU Wien)) National Institute of Informatics(日本信息处理学会) The Graduate University for Advanced Studies, SOKENDAI(高级研究大学,SOKENDAI)

AI总结 提出决策传播(DProp)方法及其可微扩展神经决策传播(NDProp),通过交替假决策和真传播高效计算稳定模型,提升神经符号推理的可扩展性和准确性。

Comments This is the full version (with appendix) of a paper appearing at the 35th International Joint Conference on Artificial Intelligence (IJCAI-ECAI 2026)

URL PDF HTML 收藏
2606.00054 2026-06-02 cs.RO cs.AI cs.CV

From Human Videos to Robot Manipulation: A Survey on Scalable Vision-Language-Action Learning with Human-Centric Data

从人类视频到机器人操作:基于人类中心数据的可扩展视觉-语言-动作学习综述

Zhiyuan Feng, Qixiu Li, Huizhi Liang, Rushuai Yang, Yichao Shen, Zhiying Du, Zhaowei Zhang, Yu Deng, Li Zhao, Hao Zhao, Zongqing Lu, Oier Mees, Marc Pollefeys, Jiaolong Yang, Baining Guo

机构 * Tsinghua University(清华大学) HKUST(香港科技大学) Xi’an Jiaotong University(西安交通大学) Fudan University(复旦大学) Microsoft Research Asia(微软亚洲研究院) Peking University(北京大学) Microsoft Zurich Project(微软苏黎世实验室)

AI总结 本文综述了如何将丰富的人类视频转化为视觉-语言-动作(VLA)模型的有效知识,分类了四种方法(潜在动作表示、预测世界模型、显式2D监督、显式3D重建),并指出了结构化非结构化视频、跨具身和视角的动作映射、以及评估协议设计三大挑战。

Comments Accepted to IJCAI 2026 Survey Track. Project page: https://aaronfengzy.github.io/HumanCentricToVLA-Survey/

URL PDF HTML 收藏
2605.28209 2026-06-02 cs.LG

Robust Contrastive Graph Clustering with Adaptive Local-Global Integration

鲁棒对比图聚类与自适应局部-全局整合

Lei Zhang, Fubo Sun, Haipeng Yang, Zhong Guan, Likang Wu

机构 * School of Computer Science and Technology, Anhui University(安徽大学计算机科学与技术学院) College of Management and Economics, Tianjin University(天津大学管理学院)

AI总结 提出一种对比图聚类框架,通过注意力机制自适应融合多尺度局部结构和全局语义原型,以解决复杂图中高阶局部结构捕获不足和全局语义忽略问题,提升聚类性能。

Comments Accepted at IJCAI 2026

URL PDF HTML 收藏
2510.25799 2026-06-02 cs.CL

LISTEN to Your Preferences: An LLM Framework for Multi-Objective Selection

LISTEN 你的偏好:面向多目标选择的LLM框架

Adam S. Jovine, Tinghan Ye, Francis Bahk, Jingjing Wang, Matthew Ford, David B. Shmoys, Peter I. Frazier

机构 * Cornell University(康奈尔大学) Georgia Institute of Technology(佐治亚理工学院)

AI总结 提出LISTEN框架,利用LLM作为决策代理,通过迭代优化内部偏好模型(LISTEN-U参数法或LISTEN-T非参数法)从自然语言中学习用户隐含偏好,实现多目标选择。

Comments Accepted at IJCAI-ECAI 2026 (the 35th International Joint Conference on Artificial Intelligence)

URL PDF HTML 收藏
2605.16451 2026-06-02 cs.LG cs.AI

Physics-Guided Geometric Diffusion for Macro Placement Generation

物理引导的几何扩散用于宏单元布局生成

Jongho Yoon, Jinsung Jeon, Seokhyeong Kang

机构 * POSTECH Institute of Artificial Intelligence(POSTECH人工智能研究所) KAIST InnoCORE LLM(韩国科学技术院InnoCORE语言模型实验室) Seoul National University(首尔国立大学) Pohang University of Science and Technology(釜山科学技术大学)

AI总结 提出MacroDiff+框架,通过双域去噪架构和物理引导采样策略,在宏单元布局中同时优化拓扑连接和物理约束,在ISPD2005 MMS基准上实现线长减少6.1-6.2%。

Comments Accepted to IJCAI 2026. 9 pages, 5 figures

URL PDF HTML 收藏
2509.16635 2026-06-02 cs.CV

Towards Anytime Retrieval: A Benchmark for Anytime Person Re-Identification

面向任意时间检索:任意时间行人重识别基准

Xulin Li, Yan Lu, Bin Liu, Jiaze Li, Qinhong Yang, Tao Gong, Qi Chu, Mang Ye, Nenghai Yu

机构 * School of Cyber Science and Technology, University of Science and Technology of China(中国科学技术大学信息科学与技术学院) Anhui Province Key Laboratory of Digital Security(安徽省数字安全重点实验室) The Chinese University of Hong Kong(香港中文大学) School of Computer Science, Wuhan University, China(武汉大学计算机科学学院)

AI总结 提出任意时间行人重识别(AT-ReID)任务,构建大规模多场景数据集AT-USTC,并设计统一模型Uni-AT实现全天候多场景有效检索。

Comments Accepted by IJCAI 2025 (oral)

URL PDF HTML 收藏
2212.06751 2026-06-02 cs.LG cs.AI

Speeding Up Multi-Objective Hyperparameter Optimization by Task Similarity-Based Meta-Learning for the Tree-Structured Parzen Estimator

基于任务相似性元学习加速多目标超参数优化的树形结构Parzen估计器

Shuhei Watanabe, Noor Awad, Masaki Onishi, Frank Hutter

机构 * Department of Computer Science, University of Freiburg, Germany(弗赖堡大学计算机科学系) Artificial Intelligence Research Center, AIST, Tokyo, Japan(日本科学技术厅人工智能研究中心)

AI总结 提出利用任务间顶级域重叠定义的任务相似性扩展TPE采集函数到元学习设置,加速多目标超参数优化,理论分析并解决相似性局限,实验证明在表格HPO基准上达到最优性能并赢得AutoML 2022竞赛。

Comments Accpeted to IJCAI 2023

URL PDF HTML 收藏
2211.14411 2026-06-02 cs.LG cs.AI

c-TPE: Tree-structured Parzen Estimator with Inequality Constraints for Expensive Hyperparameter Optimization

c-TPE: 带不等式约束的树结构Parzen估计器用于昂贵的超参数优化

Shuhei Watanabe, Frank Hutter

机构 * Department of Computer Science, University of Freiburg(弗赖堡大学计算机科学系)

AI总结 提出c-TPE方法,通过修改TPE的采样和模型以处理不等式约束,在81个昂贵HPO问题上取得最佳平均排名性能。

Comments Accepted to IJCAI 2023

URL PDF HTML 收藏
2605.31155 2026-06-01 cs.LG

Learning Hyperspherical Time-Frequency Representations for Time-Series Out-of-Distribution Detection

学习超球面时频表示用于时间序列分布外检测

Willian T. Lunardi, Samridha Shrestha, Martin Andreoni

机构 * Technology Innovation Institute(技术创新研究所) Khalifa University(哈利法大学)

AI总结 本文提出一种基于超球面嵌入的表示学习方法,通过von Mises-Fisher目标函数结合时频域编码器,实现时间序列的分布外检测,在UCR和UEA数据集上优于对比学习和后处理方法。

Comments 14 pages, 2 figures, 4 tables, accepted at IJCAI-ECAI 2026

URL PDF HTML 收藏
2601.01456 2026-06-01 cs.CV cs.AI cs.LG

Rethinking Multimodal Few-Shot 3D Point Cloud Segmentation: From Fused Refinement to Decoupled Arbitration

重新思考多模态少样本3D点云分割:从融合精炼到解耦仲裁

Wentao Bian, Fenglei Xu

机构 * Suzhou University of Science and Technology(苏州科技大学)

AI总结 针对多模态少样本3D点云分割中“融合-精炼”范式的“可塑性-稳定性困境”和CLIP的语义盲区,提出解耦专家仲裁少样本分割网络(DA-FSS),通过解耦语义与几何路径并相互正则化梯度,实现更好的泛化性能。

Comments Accepted to IJCAI-ECAI 2026 (Main Track). 9 pages, 3 figures, 3 tables

URL PDF HTML 收藏
2605.24460 2026-05-29 cs.CV cs.AI

Coarse-to-Fine Domain Incremental Learning with Attentive Distillation for Mining Footprint Segmentation in Multispectral Imagery

面向多光谱影像采矿足迹分割的粗到细领域增量学习与注意力蒸馏

Alif Tri Handoyo, Vincent C. S. Lee, Rizka Widyarini Purwanto, Alex M. Lechner, Deanna Kemp, Muhamad Risqi U. Saputra

机构 * Monash University, Indonesia(印度尼西亚莫纳什大学) Monash University, Australia(澳大利亚莫纳什大学) Northeastern University, China(中国东北大学) The University of Queensland, Australia(澳大利亚昆士兰大学)

AI总结 提出MineC2FNet框架,利用粗标注数据通过教师-学生架构和注意力蒸馏增强细粒度采矿足迹分割,解决领域偏移问题。

Comments Accepted at the 35th International Joint Conference on Artificial Intelligence (IJCAI 2026), AI and Social Good track

URL PDF HTML 收藏
2605.04916 2026-05-29 cs.AI cs.LG cs.SC

A Foundation Model for Zero-Shot Logical Rule Induction

零样本逻辑规则归纳的基础模型

Yin Jun Phua

机构 * Institute of Science Tokyo(东京科学研究所)

AI总结 提出神经规则归纳器(NRI),一种基于统计编码和并行槽解码的预训练模型,实现零样本逻辑规则归纳,无需重新训练即可泛化到新谓词。

Comments Camera-ready version accepted at IJCAI 2026, with full appendices

URL PDF HTML 收藏
2605.27431 2026-05-28 cs.LG cs.AI

Tackling Multimodal Learning Challenges with Mixture-of-Expert: A Survey

应对多模态学习挑战的混合专家方法:综述

Liangwei Nathan Zheng, Wei Emma Zhang, Olaf Maennel, Lin Yue, Weitong Chen

机构 * Adelaide University(阿德莱德大学)

AI总结 本文综述了混合专家(MoE)如何通过高效扩展、表示学习和自适应适配解决多模态学习中的可扩展性、异质性和数据不完美等核心挑战。

Comments This survey paper has just been accepted by IJCAI 2026. Results were released by 30 April 2026. As I could not find a particular place to drop the acceptance email. I have upload the acceptance email alongside the LaTeX files of the paper, named as Acceptance_email.pdf

URL PDF HTML 收藏
2605.27416 2026-05-28 quant-ph cs.AI cs.DC cs.LG

Can Quantum Federated Learning Withstand Circuit-Level Backdoors?

量子联邦学习能否抵御电路级后门攻击?

Aakar Mathur, Mohammed Ruknuddin, Ashish Gupta

机构 * BITS Pilani Dubai Campus(比斯汉尼迪拜校区)

AI总结 提出电路级后门威胁模型(CULT),通过量子感知机制(Grover、Pauli、Bit-flip、Sign-flip)实现四种隐蔽攻击,理论证明攻击的隐蔽性,实验表明单个恶意客户端即可导致FedAvg精度严重下降,现有防御无法消除最坏情况。

Comments Accepted to IJCAI-ECAI 2026

URL PDF HTML 收藏
2501.01669 2026-05-28 cs.LG cs.RO

Inversely Learning Transferable Rewards via Abstracted States

通过抽象状态逆向学习可迁移奖励

Yikang Gui, Prashant Doshi

机构 * THINC Lab, School of Computing University of Georgia(THINC实验室,计算学院,佐治亚大学) School of Computing and Institute for AI University of Georgia(计算学院和人工智能研究所,佐治亚大学)

AI总结 提出一种通过行为轨迹逆向学习抽象奖励函数的方法,并在未见过的领域实例中验证其可迁移性。

Comments Accepted at IJCAI 2026

URL PDF HTML 收藏
2605.27296 2026-05-27 cs.CL

Probing Cultural Awareness in LLMs: A Case Study of Cross-Culture Aesthetic Stylistics

探究大型语言模型的文化意识:跨文化美学文体学案例研究

Jiashuo Wang, Fenggang Yu, Jian Wang, Chak Tou Leong, Xiaoyu Shen, Chunpu Xu, Jiawen Duan, Wenjie Li, Johan F. Hoorn

机构 * Department of Computing, Hong Kong Polytechnic University(香港理工大学计算机系) Institute of Digital Twin, Eastern Institute of Technology, Ningbo(宁波东部技术研究所数字孪生研究所) Department of Language Science and Technology, Hong Kong Polytechnic University(香港理工大学语言科学与技术系) School of Design, Hong Kong Polytechnic University(香港理工大学设计学院) Research Institute for Quantum Technology, Hong Kong Polytechnic University(香港理工大学量子技术研究所) Department of Communication Science, Vrije Universiteit Amsterdam(阿姆斯特丹自由大学传播科学系)

AI总结 通过构建C4STYLI基准(包含香港和中国大陆的高度风格化翻译电影片名和广告标语),评估大型语言模型在跨文化美学文体识别和生成方面的能力,发现模型依赖表层语言信息而非风格结构,对香港特定风格结构敏感度有限。

Comments IJCAI 2026 Human-Centred AI track

URL PDF HTML 收藏
2605.26956 2026-05-27 cs.AI cs.CL

LELA: An End-to-end LLM-based Entity Linking Framework with Zero-shot Domain Adaptation

LELA: 一种基于LLM的端到端实体链接框架,支持零样本领域自适应

Samy Haffoudhi, Nikola Dobričić, Fabian Suchanek, Nils Holzenberger

AI总结 本文提出LELA,一种基于大语言模型的模块化、领域无关的实体消歧方法,并扩展为实用的Python库,集成零样本命名实体识别,实现端到端实体链接,实验验证其跨领域性能与鲁棒性。

Journal ref 35th International Joint Conference on Artificial Intelligence (IJCAI-ECAI 2026), IJCAI (International Joint Conferences on Artificial Intelligence), Aug 2026, Bremen (DE), Germany

URL PDF HTML 收藏
2605.26191 2026-05-27 cs.LG cs.AI

Modeling Dynamic Mixtures of Time-Delay Systems from Streaming Time Series

从流式时间序列建模时滞系统的动态混合

Ren Fujiwara, Yasuko Matsubara, Yasushi Sakurai

机构 * SANKEN, The University of Osaka, Japan(SANKEN大学大阪大学日本)

AI总结 提出在线框架DelayMix,将流式时间序列视为时滞系统的动态混合,通过固定长度表示总结过去状态,利用马尔可夫参数张量捕捉动态和延迟,实现快速适应环境变化并降低内存使用。

Comments Accepted by IJCAI 2026

URL PDF HTML 收藏
2605.22904 2026-05-27 cs.CV cs.AI

Suicide Risk Assessment from AI-powered Video Surveillance: An Interpretable Framework for Prevention in Metro Stations

基于AI视频监控的自杀风险评估:地铁站预防的可解释框架

Safwen Naimi, Wassim Bouachir, Guillaume-Alexandre Bilodeau, Brian Mishara

机构 * Université TÉLUQ(大学TÉLUQ) Polytechnique Montréal(蒙特利尔理工学院) Université du Québec à Montréal(魁北克大学蒙特利尔分校)

AI总结 提出首个可解释框架,通过行人跟踪、活动识别、站台语义分割和轨迹风险热图建模,从监控视频中评估自杀风险,在真实数据上达到83.2% ROC-AUC。

Comments 9 pages, 6 figures, 1 table. Accepted for Publication in the International Joint Conference of Artificial Intelligence (IJCAI)

URL PDF HTML 收藏
2404.18539 2026-05-27 cs.CV cs.AI

Enhancing Boundary Segmentation for Topological Accuracy with Skeleton-based Methods

基于骨架的方法增强边界分割的拓扑准确性

Chuni Liu, Boyuan Ma, Xiaojuan Ban, Yujie Xie, Hao Wang, Weihua Xue, Jingchao Ma, Ke Xu

机构 * University of Science and Technology Beijing(北京科技大学) Beijing Advanced Innovation Center for Materials Genome Engineering(北京材料基因组创新中心) School of Intelligence Science and Technology(智能科学与技术学院) Shunde Innovation School(顺德创新学校) Institute for Advanced Materials and Technology(先进材料与技术研究院) Key Laboratory of Intelligent Bionic Unmanned Systems(智能仿生无人系统重点实验室) Institute of Materials Intelligent Technology(材料智能技术研究院) Liaoning Academy of Materials(辽宁省材料科学院) School of Materials Science and Technology(材料科学与技术学院)

AI总结 提出Skea-Topo Aware损失函数,通过骨架感知加权和边界修正项提升网状图像边界分割的拓扑一致性,在三个数据集上相比13种方法VI指标提升最多7点。

Journal ref Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence (IJCAI-24), pp. 1092-1100, 2024

URL PDF HTML 收藏
2605.25495 2026-05-26 cs.RO cs.CV

RepSAM: Bridging Foundation Models to Robotic Vision via Representation-Guided Adaptation

RepSAM: 通过表示引导的适应连接基础模型与机器人视觉

Wenhui Chu

机构 * Department of Computer Science and Engineering, Texas A&M University(计算机科学与工程系,德克萨斯大学阿马尔科分校)

AI总结 针对基础模型在非结构化机器人视觉场景中性能下降的问题,提出RepSAM框架,通过CKA引导的秩分配策略和多模态融合模块实现参数高效微调,在减少158倍可训练参数的同时达到全微调97.9%的性能。

Comments Accepted to IJCAI-ECAI 2026 (Special Track on AI and Robotics). 8 pages, 4 figures, 12 tables

URL PDF HTML 收藏
2605.23473 2026-05-26 cs.LG cs.AI

Automated Random Embedding for Practical Bayesian Optimization with Unknown Effective Dimension

面向未知有效维度的实用贝叶斯优化的自动随机嵌入

Hong Qian, Xiang Shu, Xiang Xia, Xuhui Liu, Yangde Fu, Bei Liang, Huibin Wang, Liang Dou

机构 * Shanghai Institute of AI for Education, and School of Computer Science and Technology, East China Normal University(上海人工智能教育研究院,东华大学计算机科学与技术学院) Ant Group(蚂蚁集团) Nanjing University(南京大学)

AI总结 提出动态共享嵌入贝叶斯优化(DSEBO)方法,通过自动调整子空间维度并共享查询解,平衡近似与优化误差,在高维优化中显著降低遗憾和时间成本。

Comments This paper has been accepted by IJCAI 2026

URL PDF HTML 收藏