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

共收录 2909
2602.00209 2026-02-03 cs.MM

Divide and Conquer: Multimodal Video Deepfake Detection via Cross-Modal Fusion and Localization

分而治之:通过跨模态融合与定位实现多模态视频深度伪造检测

Qingcao Li, Miao He, Liang Yi, Qing Wen, Yitao Zhang, Hongshuo Jin, Peng Cheng, Zhongjie Ba, Li Lu, Kui Ren

AI总结 本文提出一种通过跨模态融合与定位实现多模态视频深度伪造检测的系统,通过音频和视觉模块的融合提升检测鲁棒性。

Comments The 3rd Place, IJCAI 2025 Workshop on Deepfake Detection, Localization, and Interpretability

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.22589 2026-02-02 cs.LG cs.AI

FedCARE: Federated Unlearning with Conflict-Aware Projection and Relearning-Resistant Recovery

FedCARE: 联邦去学习与冲突感知投影及抗重新学习恢复

Yue Li, Mingmin Chu, Xilei Yang, Da Xiao, Ziqi Xu, Wei Shao, Qipeng Song, Hui Li

机构 * School of Cyber Engineering, Xidian University(电子科技大学信息工程学院) RMIT University(皇家墨尔本理工大学) Commonwealth Scientific and Industrial Research Organisation (CSIRO)(澳大利亚联邦科学与工业研究组织) UNSW Sydney(新南威尔士大学悉尼分校) University of California, Davis(加州大学戴维斯分校)

AI总结 FedCARE通过冲突感知投影和抗重新学习恢复,实现高效的联邦去学习,提升效用保留并降低重新学习风险。

Comments 9 pages, 4 figures. Submitted to IJCAI 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.16835 2026-01-26 cs.GT

Multi-Agent Non-Discriminatory Contracts

多智能体非歧视合同

Ke Ding, Bo Li, Ankang Sun

AI总结 本文研究多智能体合同中委托人效用最大化与支付平等之间的权衡,提出非歧视价格的界并分析其与非歧视程度的关系。

Comments 22 pages, submitted to IJCAI 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.16511 2026-01-26 cs.GT

Participatory Budgeting Project Strength via Candidate Control

通过候选人控制强化参与式预算项目

Piotr Faliszewski, Łukasz Janeczko, Dušan Knop, Jan Pokorný, Šimon Schierreich, Mateusz Słuszniak, Krzysztof Sornat

AI总结 本文研究了参与式预算选举中通过候选人控制确保胜出的复杂性,证明了多种规则下的NP难性,并通过实验展示了删除候选人对评估项目性能的作用。

Comments A preliminary version appeared in IJCAI '25

详情

展开后加载摘要…

URL PDF HTML 收藏
2209.15635 2026-01-26 cs.LG cs.IR

Vertical Semi-Federated Learning for Efficient Online Advertising

垂直半联邦学习用于高效在线广告

Wenjie Li, Shu-Tao Xia, Jiangke Fan, Teng Zhang, Xingxing Wang

机构 * Tsinghua Shenzhen International Graduate School, Tsinghua University(清华大学深圳国际研究生院)

AI总结 本文提出垂直半联邦学习方法,通过联合特权学习框架解决传统垂直联邦学习在适用范围和实时服务中的局限,提升在线广告系统的效率和效果。

Comments TheWebConf 2026 short (proceedings). An earlier version was presented at the FL workshop of IJCAI 2023 (non-proceedings)

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.14840 2026-01-22 cs.AI cs.RO cs.SE

Implementing Knowledge Representation and Reasoning with Object Oriented Design

基于面向对象设计的知识表示与推理实现

Abdelrhman Bassiouny, Tom Schierenbeck, Sorin Arion, Benjamin Alt, Naren Vasantakumaar, Giang Nguyen, Michael Beetz

机构 * AICOR Institute for Artificial Intelligence(AICOR人工智能研究所) University of Bremen(不莱梅大学)

AI总结 KRROOD通过面向对象设计实现知识表示与推理,有效整合了软件工程与KR&R系统,支持复杂任务学习和自主系统推理。

Comments 9 pages, 2 figures, submitted to the 2026 International Joint Conference on Artificial Intelligence (IJCAI)

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.12747 2026-01-21 cs.CV

SSPFormer: Self-Supervised Pretrained Transformer for MRI Images

SSPFormer: 用于MRI图像的自监督预训练Transformer

Jingkai Li, Xiaoze Tian, Yuhang Shen, Jia Wang, Dianjie Lu, Guijuan Zhang, Zhuoran Zheng

机构 * Qilu University of Technology(青岛科技大学) Second Hospital of Shandong University(山东大学第二医院) Shandong Normal University(山东师范大学)

AI总结 SSPFormer通过自监督预训练和反频率投影掩码等方法,提升MRI图像处理的领域适应性和鲁棒性,实现分割、超分辨率和去噪任务的高性能表现。

Comments Undergraduate student as first author submitted to IJCAI

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.01969 2026-01-21 cs.CV

MC3D-AD: A Unified Geometry-aware Reconstruction Model for Multi-category 3D Anomaly Detection

MC3D-AD:一种多类3D异常检测的统一几何感知重建模型

Jiayi Cheng, Can Gao, Jie Zhou, Jiajun Wen, Tao Dai, Jinbao Wang

AI总结 MC3D-AD通过统一的几何感知重建模型实现多类3D异常检测,提升重建能力和检测性能。

Comments 7 pages of main text, 3 pages of appendix, accepted to IJCAI 2025

Journal ref https://www.ijcai.org/proceedings/2025/94

详情

展开后加载摘要…

URL PDF HTML 收藏
2405.03467 2026-01-21 cs.GT cs.DM

Welfare Loss in Connected Resource Allocation

连接资源分配中的福利损失

Xiaohui Bei, Alexander Lam, Xinhang Lu, Warut Suksompong

AI总结 研究连接资源分配中的福利损失,提出平等和功利连接价格概念,并为不同图结构给出连接价格的界限。

Comments Appears in the 33rd International Joint Conference on Artificial Intelligence (IJCAI), 2024

Journal ref Discrete Applied Mathematics, 385:1-23 (2026)

详情

展开后加载摘要…

URL PDF HTML 收藏
2411.10775 2026-01-19 eess.IV cs.CV cs.MM

Beyond Feature Mapping GAP: Integrating Real HDRTV Priors for Superior SDRTV-to-HDRTV Conversion

超越特征映射GAP:整合真实HDRTV先验以实现更优SDRTV到HDRTV转换

Gang He, Kepeng Xu, Li Xu, Siqi Wang, Wenxin Yu, Xianyun Wu

机构 * Xidian University(西电大学) Southwest University of Science and Technology(西南科技大学)

AI总结 本文提出基于真实HDRTV先验的SDRTV到HDRTV转换方法,通过两阶段模型提升转换精度和可靠性。

Comments accepted by IJCAI 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2206.13405 2026-01-19 cs.LG cs.AI stat.ML

Utilizing Class Separation Distance for the Evaluation of Corruption Robustness of Machine Learning Classifiers

利用类别分离距离评估机器学习分类器的鲁棒性

Georg Siedel, Silvia Vock, Andrey Morozov, Stefan Voß

机构 * Federal Institute for Occupational Safety and Health (BAuA) Germany(德国职业安全与健康联邦研究所) University of Stuttgart, Germany(斯图加特大学)

AI总结 本文提出利用类别分离距离评估分类器的破坏鲁棒性,通过数据增强方法改进鲁棒性并提升准确率。

Comments Accepted for the IJCAI-ECAI-22 Workshop on Artificial Intelligence Safety (AISafety 2022) We made an important correction in the abstract compared to the published version, changing "mean corruption corruption robustness" to "minimal separation corruption robustness" which is the correct name of our proposed metric

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.08519 2026-01-14 cs.CV cs.AI

CD^2: Constrained Dataset Distillation for Few-Shot Class-Incremental Learning

CD²:约束数据集蒸馏用于少样本类增量学习

Kexin Bao, Daichi Zhang, Hansong Zhang, Yong Li, Yutao Yue, Shiming Ge

机构 * Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所) School of Cyber Security, University of Chinese Academy of Sciences(中国科学院大学网络安全学院) Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州))

AI总结 CD²通过约束数据集蒸馏方法,在少样本类增量学习中有效缓解灾难性遗忘问题,提升模型对先前知识的保留能力。

Journal ref International Joint Conferences on Artificial Intelligence (IJCAI) 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.06974 2026-01-13 cs.CL

UETQuintet at BioCreative IX -- MedHopQA: Enhancing Biomedical QA with Selective Multi-hop Reasoning and Contextual Retrieval

UETQuintet在BioCreative IX上的MedHopQA:通过选择性多跳推理和上下文检索增强生物医学问答

Quoc-An Nguyen, Thi-Minh-Thu Vu, Bich-Dat Nguyen, Dinh-Quang-Minh Tran, Hoang-Quynh Le

机构 * VNU University of Engineering and Technology(越南工程大学)

AI总结 本文提出MedHopQA模型,通过选择性多跳推理和上下文检索提升生物医学问答性能,在BioCreative IX共享任务中取得第二名成绩。

Comments In Proceedings of the BioCreative IX Challenge and Workshop (BC9): Large Language Models for Clinical and Biomedical NLP, IJCAI 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2501.17802 2026-01-12 cs.LG

LEKA:LLM-Enhanced Knowledge Augmentation

LEKA:大语言模型增强的知识增强

Xinhao Zhang, Jinghan Zhang, Fengran Mo, Dongjie Wang, Yanjie Fu, Kunpeng Liu

机构 * Portland State University(波特兰州立大学) University of Montreal(蒙特利尔大学) University of Kansas(堪萨斯大学) Arizona State University(亚利桑那州立大学)

AI总结 LEKA通过主动检索合适知识源,提升跨领域知识转移效率,减少计算成本并优化迁移学习效果。

Comments Accepted by IJCAI 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2406.03505 2026-01-12 cs.LG cs.AI

Dynamic and Adaptive Feature Generation with LLM

动态和自适应特征生成与大语言模型

Xinhao Zhang, Jinghan Zhang, Banafsheh Rekabdar, Yuanchun Zhou, Pengfei Wang, Kunpeng Liu

机构 * Portland State University(波特兰州立大学) Computer Network Information Center, Chinese Academy of Sciences(中国科学院计算机网络信息中心) University of Chinese Academy of Sciences, Chinese Academy of Sciences(中国科学院大学)

AI总结 本文提出利用大语言模型和特征生成提示,实现动态和自适应的特征生成方法,以提高特征生成的可解释性、适用性和灵活性。

Comments Accepted by IJCAI 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.04544 2026-01-09 cs.AI

TCAndon-Router: Adaptive Reasoning Router for Multi-Agent Collaboration

TCAndon-Router: 多智能体协作的自适应推理路由

Jiuzhou Zhao, Chunrong Chen, Chenqi Qiao, Lebin Zheng, Minqi Han, Yanchi Liu Yongzhou Xu Xiaochuan Xu Min Zhang

机构 * Tencent Cloud Andon(腾讯云安顿)

AI总结 TCAndon-Router通过动态智能体接入和自然语言推理链提升多智能体协作的路由准确性与鲁棒性。

Comments 16 pages, 6 figures. Under review at IJCAI

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.04507 2026-01-09 cs.CE cs.AI

A Semi-supervised Molecular Learning Framework for Activity Cliff Estimation

一种用于活动悬崖估计的半监督分子学习框架

Fang Wu

机构 * Stanford University(斯坦福大学)

AI总结 本文提出SemiMol框架,通过半监督学习解决活动悬崖问题,提升基于图的ML模型性能。

Journal ref Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence 2024

详情

展开后加载摘要…

URL PDF HTML 收藏
2407.19204 2026-01-08 cs.CY cs.AI

Towards the Terminator Economy: Assessing Job Exposure to AI through LLMs

迈向终止经济:通过大语言模型评估工作对AI的暴露

Emilio Colombo, Fabio Mercorio, Mario Mezzanzanica, Antonio Serino

机构 * Dept of International Economics, Institutions and Development, Catholic University of Milan(国际经济学、机构与发展系,米兰天主教大学) Dept of Statistics and Quantitative Methods, University of Milano-Bicocca, Italy(统计与定量方法系,米兰-比科卡大学,意大利) CRISP Research Centre, University of Milano-Bicocca, Italy(CRISP研究中心,米兰-比科卡大学,意大利) Dept of Economics, Management and Statistics, University of Milano-Bicocca(经济学、管理与统计系,米兰-比科卡大学)

AI总结 通过大语言模型评估工作对AI的暴露度,揭示AI对就业和生产力的积极影响及职业间互补性。

Comments 10 pages. Accepted for publication at IJCAI 2025. Final version available at https://doi.org/10.24963/ijcai.2025/1066

Journal ref Proceedings of the 34th International Joint Conference on Artificial Intelligence (IJCAI 2025), article no. 1066

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.03166 2026-01-07 cs.LG

Dynamic Hyperparameter Importance for Efficient Multi-Objective Optimization

动态超参数重要性用于高效多目标优化

Daphne Theodorakopoulos, Marcel Wever, Marius Lindauer

机构 * Institute of Artificial Intelligence (LUH | | AI)(人工智能研究所) Leibniz University Hannover(汉诺威莱比锡大学) L3S Research Center(L3S研究中心)

AI总结 本文提出了一种动态优化方法,通过动态调整超参数重要性来提高多目标优化的效率和效果。

Comments Submitted to IJCAI 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.17689 2025-12-22 stat.ML cs.LG stat.ME

Imputation Uncertainty in Interpretable Machine Learning Methods

可解释机器学习方法中的填补不确定性

Pegah Golchian, Marvin N. Wright

机构 * Leibniz Institute for Prevention Research & Epidemiology – BIPS(预防研究与流行病学研究所) Faculty of Mathematics and Computer Science, University of Bremen(数学与计算机科学学院)

AI总结 研究探讨了可解释机器学习方法中不同填补技术对置信区间覆盖概率的影响,发现单一填补会导致方差低估,而多重填补更接近预期覆盖水平。

Comments 19 pages, 15 Figures, accepted at conference: IJCAI 2025 Workshop on Explainable Artificial Intelligence (Montreal, Canada)

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.04461 2025-12-19 cs.LG cs.AI cs.SI

A Survey on Temporal Interaction Graph Representation Learning: Progress, Challenges, and Opportunities

时间交互图表示学习的综述:进展、挑战与机遇

Pengfei Jiao, Hongjiang Chen, Xuan Guo, Zhidong Zhao, Dongxiao He, Di Jin

机构 * Hangzhou Dianzi University(杭州电子科技大学) Tianjin University(天津大学)

AI总结 本文综述了时间交互图表示学习的进展、挑战与机遇,系统分类了最新方法并探讨了未来研究方向。

Comments IJCAI 2025 Survey Track

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.14273 2025-12-16 cs.LG cs.AI cs.NE cs.SC

X-KAN: Optimizing Local Kolmogorov-Arnold Networks via Evolutionary Rule-Based Machine Learning

X-KAN:通过基于规则的机器学习框架优化局部Kolmogorov-Arnold网络

Hiroki Shiraishi, Hisao Ishibuchi, Masaya Nakata

机构 * Faculty of Engineering, Yokohama National University(Yokohama国立大学工学部) Department of Computer Science and Engineering, Southern University of Science and Technology(南方科技大学计算机科学与工程系)

AI总结 X-KAN通过基于规则的机器学习框架优化局部Kolmogorov-Arnold网络,有效提升复杂和不连续函数的近似精度。

Comments Accepted by the 34th International Joint Conference on Artificial Intelligence (IJCAI 2025)

Journal ref 34th International Joint Conference on Artificial Intelligence (IJCAI 2025)

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.11502 2025-12-15 cs.CL

Building Patient Journeys in Hebrew: A Language Model for Clinical Timeline Extraction

用希伯来语构建患者旅程:一种用于临床时间线提取的语言模型

Kai Golan Hashiloni, Brenda Kasabe Nokai, Michal Shevach, Esthy Shemesh, Ronit Bartin, Anna Bergrin, Liran Harel, Nachum Dershowitz, Liat Nadai Arad, Kfir Bar

机构 * Efi Arazi School of Computer Science, Reichman University, Herzilya, Israel(Reichman大学埃菲·阿拉兹计算机科学学院) Tel Aviv Sourasky Medical Center, Israel(特拉维夫 Sourasky 医院) School of Computer Science and AI, Tel Aviv University, Israel(特拉维夫大学计算机科学与人工智能学院)

AI总结 本文提出一种希伯来语医学语言模型,用于从电子健康记录中提取结构化临床时间线,以构建患者旅程,并通过两个新数据集验证了其有效性。

Comments In Proceedings of the Workshop on Large Language Models and Generative AI for Health Informatics 2025, IJCAI 2025, Montreal, Canada

详情

展开后加载摘要…

URL PDF HTML 收藏
2408.01826 2025-12-08 cs.CV

GLDiTalker: Speech-Driven 3D Facial Animation with Graph Latent Diffusion Transformer

GLDiTalker: 基于图潜在扩散变换器的语音驱动3D面部动画

Yihong Lin, Zhaoxin Fan, Xianjia Wu, Lingyu Xiong, Liang Peng, Xiandong Li, Wenxiong Kang, Songju Lei, Huang Xu

机构 * South China University of Technology(南方科技大学) Beihang University(北航) Huawei Cloud(华为云) Nanjing University(南京大学)

AI总结 GLDiTalker通过图潜在扩散变换器解决语音驱动3D面部动画中的模态不一致问题,提升唇形同步精度和运动多样性。

Comments 9 pages, 5 figures

Journal ref the 34th International Joint Conference on Artificial Intelligence, 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.04530 2025-12-05 cs.LG

Explainable Graph Representation Learning via Graph Pattern Analysis

通过图模式分析实现可解释的图表示学习

Xudong Wang, Ziheng Sun, Chris Ding, Jicong Fan

机构 * School of Data Science, The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen)(数据科学学院,香港中文大学(深圳)) Shenzhen Research Institute of Big Data(深圳大数据研究院)

AI总结 本文提出PXGL-GNN框架,通过图模式分析实现图表示的可解释性,解决了传统方法在节点特征忽略和高维问题上的局限。

Comments Full version with appendix of the paper published in the Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence (IJCAI-25), Main Track

Journal ref Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence (IJCAI-25), Main Track, pages 3426-3434, 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.01115 2025-12-02 cs.LG

Exploring Equity of Climate Policies using Multi-Agent Multi-Objective Reinforcement Learning

探讨气候政策的公平性:基于多智能体多目标强化学习的多目标优化

Palok Biswas, Zuzanna Osika, Isidoro Tamassia, Adit Whorra, Jazmin Zatarain-Salazar, Jan Kwakkel, Frans A. Oliehoek, Pradeep K. Murukannaiah

机构 * Delft University of Technology(代尔夫特理工大学)

AI总结 本文提出Justice框架,结合多目标多智能体强化学习与整合评估模型,以生成兼顾公平性与气候经济目标的政策建议。

Comments Published at IJCAI 2025, AI and Social Good Track

详情

展开后加载摘要…

URL PDF HTML 收藏
2406.10087 2025-11-21 cs.LG cs.AI stat.ML

Provably Robust Pre-Trained Ensembles for Biomarker-Based Cancer Classification

可证明稳健的预训练集成模型用于基于生物标志物的癌症分类

Chongmin Lee, Jihie Kim

机构 * Harvard University(哈佛大学) Dongguk University(东国大学)

AI总结 本文提出可证明稳健的预训练集成模型,用于基于生物标志物的癌症分类,实现高准确率和稳健性,同时减少特征使用和调优需求。

Comments Accepted to the AIAA Workshop at IJCAI 2024

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.19367 2025-11-20 cs.RO cs.AI cs.HC

Inference of Human-derived Specifications of Object Placement via Demonstration

Alex Cuellar, Ho Chit Siu, Julie A Shah

机构 * Massachusetts Institute of Technology(麻省理工学院) MIT Lincoln Laboratory(MIT林肯实验室)

Comments IJCAI'25

Journal ref Cuellar, Alex, Ho Chit Siu, and Julie A. Shah. ''Inference of Human-Derived Specifications of Object Placement via Demonstration''. Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25, 8 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.13186 2025-11-18 cs.LG cs.SY eess.SY

DiffFP: Learning Behaviors from Scratch via Diffusion-based Fictitious Play

Akash Karthikeyan, Yash Vardhan Pant

机构 * Department of Electrical and Computer Engineering, University of Waterloo(滑铁卢大学电气与计算机工程系)

Comments Initial results presented at the IJCAI 2025 Workshop on User-Aligned Assessment of Adaptive AI Systems. Project page: https://aku02.github.io/projects/difffp/

详情

展开后加载摘要…

URL PDF HTML 收藏
2306.06031 2025-11-18 q-fin.ST cs.CL cs.LG q-fin.TR

FinGPT: Open-Source Financial Large Language Models

Hongyang Yang, Xiao-Yang Liu, Christina Dan Wang

机构 * AI4Finance Foundation(AI4Finance基金会) Columbia University(哥伦比亚大学) New York University Shanghai(纽约大学上海)

Comments Accepted by the FinLLM Symposium at IJCAI 2023. Recipient of the Best Presentation Award (Hongyang Yang). Workshop link: https://finllm.github.io/workshop. This is the first official FinGPT paper; please cite this work when referencing FinGPT

详情

展开后加载摘要…

URL PDF HTML 收藏