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
2604.06403 2026-04-09 cs.CL cs.AI

FMI@SU ToxHabits: Evaluating LLMs Performance on Toxic Habit Extraction in Spanish Clinical Texts

FMI@SU ToxHabits:评估LLMs在西班牙临床文本中毒瘾习惯提取性能

Sylvia Vassileva, Ivan Koychev, Svetla Boytcheva

机构 * Faculty of Mathematics and Informatics, Sofia University St. Kliment Ohridski(索非亚大学圣克利门特奥赫里德斯基数学与信息学学院)

AI总结 本文提出了一种识别西班牙临床文本中毒瘾习惯实体的方法,通过LLMs在零样本、少样本和提示优化中发现GPT-4.1在少样本提示下表现最佳,达到0.65的F1分数,展示了非英语语言命名实体识别的潜力。

Comments 8 pages, 1 figure, 6 tables, Challenge and Workshop BC9 Large Language Models for Clinical and Biomedical NLP, International Joint Conference on Artificial Intelligence IJCAI 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2302.00797 2026-04-07 cs.AI cs.GT cs.LG cs.MA

Combining Tree-Search, Generative Models, and Nash Bargaining Concepts in Game-Theoretic Reinforcement Learning

将树搜索、生成模型和纳什谈判概念结合在博弈论强化学习中

Zun Li, Marc Lanctot, Kevin R. McKee, Luke Marris, Ian Gemp, Daniel Hennes, Paul Muller, Kate Larson, Yoram Bachrach, Michael P. Wellman

机构 * Google DeepMind(谷歌DeepMind) University of Waterloo(滑铁卢大学) University of Michigan(密歇根大学)

AI总结 本文提出基于深度博弈论强化学习的多智能体训练框架,通过生成最佳响应算法GenBR和纳什谈判理论构建对手混合策略,提升在不完全信息域中的对手建模能力。

Comments Accepted by IJCAI'25 main track

Journal ref Proc. 34th Int. Joint Conf. Artif. Intell. (IJCAI 2025), pp. 161-169

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.01256 2026-04-07 cs.NE

Runtime Analyses of NSGA-III on Many-Objective Problems: Provable Exponential Speedup via Stochastic Population Update

NSGA-III在多目标问题上的运行时间分析:通过随机种群更新实现可证明的指数加速

Andre Opris

AI总结 本文通过严格运行时间分析,揭示NSGA-III在多目标问题上的性能,证明随机种群更新机制在多目标多模态问题中可实现指数加速。

Comments This is the long version of the paper with the title "A First Runtime Analysis of NSGA-III on a Many-Objective Multimodal Problem: Provable Exponential Speedup via Stochastic Population Update" already appeared at IJCAI 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.25699 2026-03-27 cs.LG cs.AI

Neural Network Conversion of Machine Learning Pipelines

机器学习流水线的神经网络转换

Man-Ling Sung, Jan Silovsky, Man-Hung Siu, Herbert Gish, Chinnu Pittapally

机构 * Raytheon BBN Technologies(雷神BBN科技公司)

AI总结 本文探讨了将非神经网络的机器学习流水线作为教师模型,转换为神经网络学生模型的方法,通过联合优化流水线组件实现多任务统一推理引擎。

Comments Submitted and accepted to AutoML 2018 @ ICML/IJCAI-ECAI

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.05786 2026-03-23 cs.CV cs.AI

How to Enable LLM with 3D Capacity? A Survey of Spatial Reasoning in LLM

如何使LLM具备3D能力?LLM中空间推理的综述

Jirong Zha, Yuxuan Fan, Xiao Yang, Chen Gao, Xinlei Chen

机构 * Tsinghua University(清华大学) The Hong Kong University of Science and Technology (Guang Zhou)(香港科学与技术大学(广州))

AI总结 本文综述了将LLM与3D空间理解结合的方法,提出分类体系,涵盖图像、点云和混合模态方法,并讨论了当前限制与未来研究方向。

Comments 9 pages, 5 figures

Journal ref IJCAI 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.16294 2026-03-17 cs.CV

Self-Classification Enhancement and Correction for Weakly Supervised Object Detection

自分类增强与修正用于弱监督目标检测

Yufei Yin, Lechao Cheng, Wengang Zhou, Jiajun Deng, Zhou Yu, Houqiang Li

AI总结 本文提出一种新的弱监督目标检测框架,通过自分类增强模块和修正算法解决分类模糊性和误分类问题,实验表明其在VOC数据集上表现优异。

Comments Accepted by IJCAI 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.14007 2026-03-17 cs.AI

Formal Abductive Explanations for Navigating Mental Health Help-Seeking and Diversity in Tech Workplaces

形式归纳解释用于导航心理健康求助与科技职场多样性

Belona Sonna, Alain Momo, Alban Grastien

AI总结 本文提出形式归纳解释框架,用于系统揭示AI对科技职场心理健康求助预测的合理性。通过计算模型输出的严谨解释,支持选择适合不同心理科目的模型,并确保伦理稳健的救济计划。同时,明确考察性别等敏感属性对模型决策的影响,以支持公平性评估。

Comments Appeared in the Proceedings of the Empowering Women of Colour in AI-Driven Mental Health Research at IJCAI 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.00744 2026-03-17 cs.CV

Localizing Before Answering: A Hallucination Evaluation Benchmark for Grounded Medical Multimodal LLMs

先定位后回答:一种用于基于地面的医学多模态大语言模型的幻觉评估基准

Dung Nguyen, Minh Khoi Ho, Huy Ta, Thanh Tam Nguyen, Qi Chen, Kumar Rav, Quy Duong Dang, Satwik Ramchandre, Son Lam Phung, Zhibin Liao, Minh-Son To, Johan Verjans, Phi Le Nguyen, Vu Minh Hieu Phan

AI总结 本文提出HEAL-MedVQA基准,通过创新评估协议和67K VQA数据集,评估医学多模态模型的定位能力与幻觉鲁棒性,提出LobA框架提升视觉推理能力,实验结果表明其在挑战性基准中优于现有生物医学LMMs。

Comments Accepted at Joint Conference on Artificial Intelligence (IJCAI) 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.13168 2026-03-16 cs.AI cs.CL cs.IR

Developing and evaluating a chatbot to support maternal health care

开发和评估一个支持产科保健的聊天机器人

Smriti Jha, Vidhi Jain, Jianyu Xu, Grace Liu, Sowmya Ramesh, Jitender Nagpal, Gretchen Chapman, Benjamin Bellows, Siddhartha Goyal, Aarti Singh, Bryan Wilder

机构 * Carnegie Mellon University(卡内基梅隆大学) Population Council Institute(人口理事会研究所) Sitaram Bhartia Institute of Science and Research(西塔拉姆·巴提亚科学与研究研究所) Nivi, Inc.(Nivi公司)

AI总结 本文开发了一个印度产科保健聊天机器人,结合分阶段分诊、混合检索和证据引导生成,通过多方法评估验证了多语言噪声环境下医疗助手的可靠性。

Comments 17 pages; submitted to IJCAI 2026 AI and Social Good Track

详情

展开后加载摘要…

URL PDF HTML 收藏
2405.18664 2026-03-10 cs.LG cs.AI

Fast Explanations via Policy Gradient-Optimized Explainer

通过策略梯度优化的解释器实现快速解释

Deng Pan, Nuno Moniz, Nitesh Chawla

机构 * Lucy Family Institute for Data & Society(数据与社会卢西家族研究所) University of Notre Dame(北达科他大学)

AI总结 本文提出Fast Explanation框架,通过策略梯度优化实现高效模型解释,显著降低推理时间和内存使用,同时保持高质量解释和广泛适用性。

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

Journal ref Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence (IJCAI-2025), Main Track, pp. 475-483

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.06200 2026-03-09 cs.CV

Adaptive Language-Aware Image Reflection Removal Network

自适应语言感知图像反光去除网络

Siyan Fang, Yuntao Wang, Jinpu Zhang, Ziwen Li, Yuehuan Wang

机构 * Huazhong University of Science and Technology(华中科技大学) National University of Defense Technology(国防科技大学)

AI总结 ALANet通过自适应语言感知策略有效去除复杂反光,提升语言引导下的反光去除性能。

Comments IJCAI 2025

Journal ref Proceedings of the 34th International Joint Conference on Artificial Intelligence (IJCAI-25), pages 973-981, 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.03953 2026-03-09 cs.AI cs.SC cs.SY eess.SY

Handling Infinite Domain Parameters in Planning Through Best-First Search with Delayed Partial Expansions

通过延迟部分扩展的优先级搜索处理无限域参数

Ángel Aso-Mollar, Diego Aineto, Enrico Scala, Eva Onaindia

机构 * Valencian Research Institute for Artificial Intelligence (VRAIN)(瓦伦西亚人工智能研究 institute) Universitat Politècnica de València(瓦伦西亚理工大学) Università degli Studi di Brescia(布雷西亚大学)

AI总结 本文提出了一种通过延迟部分扩展的优先级搜索算法,以处理无限域参数的规划问题,证明了其在极限情况下的完备性。

Journal ref Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence. 2025. Main Track. Pages 8456-8464

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.03177 2026-03-04 cs.AI

Neuro-Symbolic Artificial Intelligence: A Task-Directed Survey in the Black-Box Models Era

神经符号人工智能:在黑盒模型时代任务导向的综述

Giovanni Pio Delvecchio, Lorenzo Molfetta, Gianluca Moro

AI总结 本研究综述探讨神经符号方法在任务导向中的进展,旨在提升可解释性和推理能力,并为现实任务提供可解释的NeSy方法资源。

Comments Accepted for publication at IJCAI-25. Please cite the definitive, copyrighted, peer reviewed and edited version of this Article published in IJCAI 25, pp. 4196-4176, 2025. DOI: https://doi.org/10.24963/ijcai.2025/1157

Journal ref Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, 2025, pages 10418-10426

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.02628 2026-03-04 cs.LG

Post Hoc Extraction of Pareto Fronts for Continuous Control

事后提取帕累托前沿用于连续控制

Raghav Thakar, Gaurav Dixit, Kagan Tumer

机构 * The Collaborative Robotics and Intelligent Systems (CoRIS) Institute(协作机器人与智能系统研究所)

AI总结 MAPEX是一种离线多目标强化学习方法,通过重用预训练策略和回放缓冲区,以低样本成本提取帕累托前沿,平衡多个目标。

Comments 10 pages, 4 figures. Submitted to IJCAI 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.01806 2026-03-03 cs.SI cs.GR cs.LG

GCTAM: Global and Contextual Truncated Affinity Combined Maximization Model For Unsupervised Graph Anomaly Detection

GCTAM: 全局和上下文截断亲和力结合最大化模型用于无监督图异常检测

Xiong Zhang, Hong Peng, Zhenli He, Cheng Xie, Xin Jin, Hua Jiang

机构 * School of Software, Yunnan University, Kunming, China(云南大学软件学院,昆明,中国)

AI总结 本文提出GCTAM模型,结合上下文和全局亲和力截断,提升无监督图异常检测效果。

Comments Accepted by IJCAI 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2204.10762 2026-03-02 cs.CV

Dite-HRNet: Dynamic Lightweight High-Resolution Network for Human Pose Estimation

Dite-HRNet:动态轻量级高分辨率网络用于人体姿态估计

Qun Li, Ziyi Zhang, Fu Xiao, Feng Zhang, Bir Bhanu

AI总结 Dite-HRNet通过动态分割卷积和自适应上下文建模,实现了高效的人体姿态估计,优于现有轻量级网络。

Comments Accepted by IJCAI-ECAI 2022

Journal ref International Joint Conference on Artificial Intelligence, pp. 1095-1101, 2022

详情

展开后加载摘要…

URL PDF HTML 收藏
2402.01446 2026-03-02 cs.MA cs.AI cs.RO

Guidance Graph Optimization for Lifelong Multi-Agent Path Finding

为终身多智能体路径寻找设计的引导图优化

Yulun Zhang, He Jiang, Varun Bhatt, Stefanos Nikolaidis, Jiaoyang Li

AI总结 本文提出引导图优化方法,用于自动为终身多智能体路径寻找生成高效引导,提升算法吞吐量。

Comments Accepted to International Joint Conference on Artificial Intelligence (IJCAI), 2024

详情

展开后加载摘要…

URL PDF HTML 收藏
2401.17044 2026-03-02 cs.AI cs.GT cs.MA

Scalable Mechanism Design for Multi-Agent Path Finding

可扩展的多智能体路径寻找机制设计

Paul Friedrich, Yulun Zhang, Michael Curry, Ludwig Dierks, Stephen McAleer, Jiaoyang Li, Tuomas Sandholm, Sven Seuken

机构 * ETH AI Center(瑞士联邦理工学院人工智能中心) University of Zurich(苏黎世大学) Carnegie Mellon University(卡内基梅隆大学) Harvard University(哈佛大学) University of Illinois at Chicago(伊利诺伊大学香槟分校) Optimized Markets, Strategy Robot, Strategic Machine(优化市场、策略机器人、战略机器)

AI总结 本文提出三种可扩展的多智能体路径寻找机制设计方法,通过策略证明机制和近似算法提升路径规划的福利效果。

Comments 12 pages, 5 figures. IJCAI'24 camera-ready version

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.20163 2026-02-25 cs.SD cs.CL eess.AS

Graph Modelling Analysis of Speech-Gesture Interaction for Aphasia Severity Estimation

语音-手势交互的图模型分析用于失语症严重程度估计

Navya Martin Kollapally, Christa Akers, Renjith Nelson Joseph

AI总结 本文提出基于图神经网络的框架,通过分析语音和手势的交互来自动估计失语症严重程度。

Comments IJCAI

详情

展开后加载摘要…

URL PDF HTML 收藏
1903.07410 2026-02-19 cs.DS cs.DM

Diversity of Solutions: An Exploration Through the Lens of Fixed-Parameter Tractability Theory

解的多样性:通过固定参数 tractability 理论的视角进行探索

Julien Baste, Michael R. Fellows, Lars Jaffke, Tomáš Masařík, Mateus de Oliveira Oliveira, Geevarghese Philip, Frances A. Rosamond

AI总结 本文通过固定参数 tractability 理论研究了解的多样性问题,提出了一种将常规动态规划算法转换为多样化解算法的框架,并展示了其在多样性参数上的多项式依赖性。

Comments Accepted to Twenty-Ninth International Joint Conference on Artificial Intelligence, {IJCAI} 2020, 16 pages

Journal ref Artificial Intelligence 303, 103644:1-103644:15, 2022; Proceedings: IJCAI 2020, 1119-1125

详情
URL PDF HTML 收藏
2602.16231 2026-02-19 cs.CV

DataCube: A Video Retrieval Platform via Natural Language Semantic Profiling

DataCube: 通过自然语言语义分析实现的视频检索平台

Yiming Ju, Hanyu Zhao, Quanyue Ma, Donglin Hao, Chengwei Wu, Ming Li, Songjing Wang, Tengfei Pan

机构 * Beijing Academy of Artificial Intelligence(北京人工智能研究院)

AI总结 DataCube通过自然语言语义分析实现视频检索,提供高效的视频处理和多维检索功能。

Comments This paper is under review for the IJCAI-ECAI 2026 Demonstrations Track

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.13455 2026-02-17 cs.CL cs.AI cs.HC

Using Machine Learning to Enhance the Detection of Obfuscated Abusive Words in Swahili: A Focus on Child Safety

利用机器学习增强斯瓦希里语中隐晦侮辱性词汇的检测:聚焦儿童安全

Phyllis Nabangi, Abdul-Jalil Zakaria, Jema David Ndibwile

AI总结 本研究利用机器学习方法提升斯瓦希里语中隐晦侮辱性词汇的检测能力,旨在提高儿童网络环境的安全性。

Comments Accepted at the Second IJCAI AI for Good Symposium in Africa, hosted by Deep Learning Indaba, 7 pages, 1 figure

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.13280 2026-02-17 cs.AI

BEAGLE: Behavior-Enforced Agent for Grounded Learner Emulation

BEAGLE:行为约束的地面学习者模拟代理

Hanchen David Wang, Clayton Cohn, Zifan Xu, Siyuan Guo, Gautam Biswas, Meiyi Ma

AI总结 BEAGLE 通过整合自我调节学习理论和三种技术创新,有效模拟学生学习行为,实现对真实学习轨迹的高还原度复现。

Comments paper under submission at IJCAI

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.09469 2026-02-11 cs.CL cs.AI

NOWJ @BioCreative IX ToxHabits: An Ensemble Deep Learning Approach for Detecting Substance Use and Contextual Information in Clinical Texts

NOWJ @BioCreative IX ToxHabits: 一种用于检测临床文本中物质使用及上下文信息的集成深度学习方法

Huu-Huy-Hoang Tran, Gia-Bao Duong, Quoc-Viet-Anh Tran, Thi-Hai-Yen Vuong, Hoang-Quynh Le

机构 * University of Engineering and Technology(工程大学) University of Engineering(工程大学) Technology, Vietnam National University(技术,越南国家大学)

AI总结 本文提出了一种集成深度学习方法,用于在西班牙临床文本中检测有毒物质使用及上下文信息,实现了较高的F1和精度指标。

Journal ref Proceedings of the BioCreative IX Challenge and Workshop (BC9): Large Language Models for Clinical and Biomedical NLP at the International Joint Conference on Artificial Intelligence (IJCAI 2025)

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.06572 2026-02-09 cs.RO

The Law of Task-Achieving Body Motion: Axiomatizing Success of Robot Manipulation Actions

任务达成身体运动定律:机器人操作动作成功的公理化规范

Malte Huerkamp, Jonas Dech, Michael Beetz

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

AI总结 本文提出任务达成身体运动定律,通过公理化规范确保机器人操作动作在语义、因果和可行性方面的正确性,支持运动合成与故障诊断。

Comments 9 pages, 3 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
2505.05017 2026-02-09 cs.CL

Scalable Multi-Stage Influence Function for Large Language Models via Eigenvalue-Corrected Kronecker-Factored Parameterization

通过特征值校正的克罗内克因子化参数化实现大规模语言模型的可扩展多阶段影响函数

Yuntai Bao, Xuhong Zhang, Tianyu Du, Xinkui Zhao, Jiang Zong, Hao Peng, Jianwei Yin

机构 * Zhejiang University(浙江大学) Universal Identification Technology (Hangzhou) Co.,Ltd.(universal identification technology (hangzhou) co., ltd.) Zhejiang Normal University(浙江师范大学)

AI总结 本文提出了一种基于特征值校正的克罗内克因子化参数化的多阶段影响函数,用于解释大规模语言模型在微调后的预测归因于预训练数据,展示了其在大规模模型中的可扩展性和解释能力。

Comments 17 pages, 4 figures; accepted by IJCAI 2025

Journal ref Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence Main Track (2025) 8022-8030

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.02276 2026-02-06 cs.AI

Rewarding Explainability in Drug Repurposing with Knowledge Graphs

利用知识图谱提升药物再利用中的可解释性

Susana Nunes, Samy Badreddine, Catia Pesquita

机构 * LASIGE, Faculty of Sciences, University of Lisbon(里斯本大学科学学院LASIGE) Sony AI(索尼人工智能) University of Trento(特伦托大学) Bruno Kessler Institute(布鲁诺·凯塞林研究所)

AI总结 本文提出REx方法,利用知识图谱链接预测生成科学解释,通过奖励机制和领域本体学提升药物再利用的预测性能和解释质量。

Comments 9 pages, 4 figures, accepted at conference IJCAI 2025

Journal ref Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence (IJCAI-25), pp. 4624-4632, 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.09843 2026-02-05 cs.LG cs.AI

HGEN: Heterogeneous Graph Ensemble Networks

HGEN:异构图集成网络

Jiajun Shen, Yufei Jin, Yi He, Xingquan Zhu

机构 * Dept. of Electrical Engineering and Computer Science, Florida Atlantic University, USA(佛罗里达大学电子工程与计算机科学系) Department of Data Science, William & Mary, USA(威廉与玛丽学院数据科学系)

AI总结 HGEN通过元路径和转换优化管道集成多个学习者,提升异构图分类精度,其残差-注意力机制和相关性正则化项增强了基础学习器的多样性和准确性。

Comments The paper is in proceedings of the 34th IJCAI Conference, 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2501.16546 2026-02-05 cs.AI

Sample-Efficient Behavior Cloning Using General Domain Knowledge

基于通用领域知识的高效行为克隆

Feiyu Zhu, Jean Oh, Reid Simmons

机构 * Carnegie Mellon University(卡内基梅隆大学)

AI总结 本文提出KIM方法,通过整合大语言模型的编码能力与专家领域知识,提升行为克隆的样本效率和泛化能力。

Journal ref In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence. Article 807, 7254-7262 (2025)

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.00718 2026-02-03 cs.LG

Federated Learning at the Forefront of Fairness: A Multifaceted Perspective

联邦学习前沿的公平性:多维度视角

Noorain Mukhtiar, Adnan Mahmood, Yipeng Zhou, Jian Yang, Jing Teng, Quan Z. Sheng

机构 * School of Computing, Macquarie University(麦考瑞大学计算机学院) School of Control and Computer Engineering, North China Electric Power University(华北电力大学控制与计算机工程学院)

AI总结 本文从多维度视角探讨联邦学习中的公平性问题,分类现有公平性方法,并提出框架和未来研究方向以推动公平性在FL中的发展。

Comments 7 pages (main content), 2 pages (references), Accepted and Published Proceedings of the 34th International Joint Conference on Artificial Intelligence (IJCAI). 2025

详情

展开后加载摘要…

URL PDF HTML 收藏