KIPPO: Koopman-Inspired Proximal Policy Optimization
Comments Accepted for IJCAI 2025. This arXiv submission is the full version of the conference paper, including the appendix and supplementary material omitted from the IJCAI proceedings
期刊&会议
IJCAI
International Joint Conference on Artificial Intelligence · 会议 · Artificial Intelligence
Dynamic Replanning for Improved Public Transport Routing
机构 * Department of Data Science and AI, Monash University, Australia（数据科学与人工智能系，墨尔本大学）
Comments Accepted for publication at IJCAI 2025. 8 pages, 4 figures, 3 tables
GRAML: Goal Recognition As Metric Learning
机构 * Computer Science Department, Bar-Ilan University（巴伊兰大学计算机科学系） ； Computer Science Department, Tufts University（塔夫茨大学计算机科学系）
Comments Accepted for publication in International Joint Conference on Artificial Intelligence (IJCAI) 2025
Deep Learning for Multivariate Time Series Imputation: A Survey
机构 * PyPOTS Research（PyPOTS研究机构） ； Hong Kong University of Science and Technology（香港理工大学） ； University of Oxford（牛津大学） ； King’s College London（伦敦大学学院） ； Huawei Noah’s Ark Lab（华为诺亚实验室） ； Hong Kong University of Science and Technology (Guangzhou)（香港理工大学（广州）） ； Squirrel Ai Learning（Squirrel Ai学习机构）
Comments Accepted by IJCAI 2025
VeRecycle: Reclaiming Guarantees from Probabilistic Certificates for Stochastic Dynamical Systems after Change
机构 * Delft University of Technology（代尔夫特理工大学）
Comments accepted to IJCAI 2025
Non-Obvious Manipulability in Additively Separable and Fractional Hedonic Games
Comments Accepted paper at IJCAI'25
Randomised Optimism via Competitive Co-Evolution for Matrix Games with Bandit Feedback
机构 * School of Computer Science, University of Birmingham（计算机科学学院，伯明翰大学）
Comments 21 pages, 10 figures, accepted at IJCAI 2025
Contrastive Cross-Course Knowledge Tracing via Concept Graph Guided Knowledge Transfer
机构 * Zhejiang University（浙江大学）
Comments Accepted by IJCAI 2025
Dual-Balancing for Physics-Informed Neural Networks
机构 * Department of Computer Science, Hong Kong Baptist University（香港 Baptist 大学计算机科学系） ； Institute of High Performance Computing (IHPC), Agency for Science, Technology and Research (A*STAR)（高性能计算研究所（IHPC），科技研究局（A*STAR））
Comments Accepted at IJCAI 2025 (34th International Joint Conference on Artificial Intelligence)
OT-DETECTOR: Delving into Optimal Transport for Zero-shot Out-of-Distribution Detection
机构 * School of Computer Science and Engineering（计算机科学与工程学院） ； Centre for Smart Health（智能健康中心）
Comments Accepted to the 34th International Joint Conference on Artificial Intelligence (IJCAI 2025)
Advancing Generalization Across a Variety of Abstract Visual Reasoning Tasks
Comments Accepted to the 34th International Joint Conference on Artificial Intelligence (IJCAI 2025)
Recommender Systems for Democracy: Toward Adversarial Robustness in Voting Advice Applications
机构 * ETH Zurich（苏黎世联邦理工学院）
Comments This is the extended version of the paper, accepted at IJCAI 2025
Synthesis of Communication Policies for Multi-Agent Systems Robust to Communication Restrictions
Comments This is the extended version of the paper accepted for publication at IJCAI 2025
LiBOG: Lifelong Learning for Black-Box Optimizer Generation
机构 * Victoria University of Wellington（怀特伍德大学） ； Lingnan University（岭南大学）
Comments Accepted at IJCAI 2025. To appear
Counterfactual Explanations for Continuous Action Reinforcement Learning
机构 * University of Virginia（弗吉尼亚大学）
Comments Accepted by International Joint Conference on Artificial Intelligence (IJCAI) 2025
Adaptive Graph Unlearning
机构 * Macquarie University（麦考瑞大学）
Comments This paper has been accepted by IJCAI 2025
InnateCoder: Learning Programmatic Options with Foundation Models
Comments Accepted at IJCAI 2025
Multi-Organizational Scheduling: Individual Rationality, Optimality, and Complexity
Comments 23 pages, Accepted at IJCAI 2025
Wisdom from Diversity: Bias Mitigation Through Hybrid Human-LLM Crowds
机构 * Machine Learning Group, Université Libre de Bruxelles（布鲁塞尔自由大学机器学习组） ； AI Lab, Vrije Universiteit Brussel（布鲁塞尔自由大学人工智能实验室） ； FARI, AI for the Common-Good Institute, ULB-VUB（ULB-VUB共同利益人工智能研究所） ； Center for Human-Compatible AI, UC Berkeley（伯克利人类兼容人工智能中心）
Comments Accepted for publication in the Proceedings of the 34th International Joint Conference on Artificial Intelligence (IJCAI 2025)
Bridging Generative and Discriminative Learning: Few-Shot Relation Extraction via Two-Stage Knowledge-Guided Pre-training
机构 * University of Electronic Science and Technology of China（电子科技大学） ； Nanyang Technological University（南洋理工大学） ； Information Engineering University（信息工程大学） ； National University of Defense Technology（国防科技大学）
Comments 13 pages, 6 figures, Appear on IJCAI 2025
Imagination-Limited Q-Learning for Offline Reinforcement Learning
Comments Accepted by IJCAI 2025
Fair Submodular Maximization over a Knapsack Constraint
Comments To appear in IJCAI 2025
Logarithmic Approximations for Fair k-Set Selection
Comments To appear in IJCAI 2025
Learning Probabilistic Temporal Logic Specifications for Stochastic Systems
机构 * University of Oxford（牛津大学） ； National University of Singapore（国立新加坡大学）
Comments Full version of the paper that appears in IJCAI'25
Adaptive Gradient Learning for Spiking Neural Networks by Exploiting Membrane Potential Dynamics
Comments 14 pages, 7 figures, 8 tables, Will be published at IJCAI 2025, the 34th International Joint Conference on Artificial Intelligence
Learn to Think: Bootstrapping LLM Reasoning Capability Through Graph Representation Learning
Comments Accepted by IJCAI 2025
Dual-level Fuzzy Learning with Patch Guidance for Image Ordinal Regression
机构 * College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院） ； School of Public Health, Zhejiang University（浙江大学公共卫生学院） ； State Key Laboratory of Transvascular Implantation Devices, The Second Affiliated Hospital Zhejiang University School of Medicine（浙江大学医学院第二附属医院血管内植入装置国家重点实验室） ； Zhejiang Key Laboratory of Medical Imaging Artificial Intelligence（浙江省医学影像人工智能重点实验室） ； China Mobile (Zhejiang) Research & Innovation Institute（中国移动（浙江）研究院） ； College of Engineering, University of Notre Dame（圣母大学工程学院） ； Transvascular Implantation Devices Research Institute（血管内植入装置研究所）
Comments Accepted by IJCAI 2025
D3: Diversity, Difficulty, and Dependability-Aware Data Selection for Sample-Efficient LLM Instruction Tuning
机构 * National Key Laboratory for Novel Software Technology, Nanjing University（南京大学新型软件技术国家重点实验室） ； School of Artificial Intelligence, Nanjing University（南京大学人工智能学院） ； Algorithm Tech, Taobao & Tmall Group of Alibaba（阿里巴巴集团算法技术部） ； School of Intelligence Science and Technology, Nanjing University（南京大学智能科学与技术学院）
Comments IJCAI'25
Adversarial Attacks on Both Face Recognition and Face Anti-spoofing Models
机构 * School of Computer Science and Technology, Huazhong University of Science and Technology（华中科技大学计算机科学与技术学院） ； College of Computer Science and Technology, Jilin University（吉林大学计算机科学与技术学院） ； Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, JLU（教育部符号计算与知识工程重点实验室） ； Department of Computer Science and Software Engineering, The University of Western Australia（西澳大学计算机科学与软件工程系）
Comments Proceedings of the 34th International Joint Conference on Artificial Intelligence (IJCAI 2025)
Can We Verify Step by Step for Incorrect Answer Detection?
机构 * The Hong Kong University of Science and Technology（香港科学与技术大学）
Comments accepted to IJCAI 2025
