Toward Reliable Scientific Hypothesis Generation: Evaluating Truthfulness and Hallucination in Large Language Models
机构 * University of Virginia（弗吉尼亚大学）
Comments Accepted to IJCAI 2025
期刊&会议
IJCAI
International Joint Conference on Artificial Intelligence · 会议 · Artificial Intelligence
How to Mitigate Information Loss in Knowledge Graphs for GraphRAG: Leveraging Triple Context Restoration and Query-Driven Feedback
Comments This paper has been accepted to IJCAI 2025
Leveraging MLLM Embeddings and Attribute Smoothing for Compositional Zero-Shot Learning
机构 * School of Computer Science and Technology, Beijing Jiaotong University（计算机科学与技术学院，北京交通大学） ； Qifu Technology（启福科技）
Comments Accepted by IJCAI 2025
Generating Grounded Responses to Counter Misinformation via Learning Efficient Fine-Grained Critiques
机构 * School of Computing Technologies, RMIT University（计算技术学院，拉筹纳斯大学）
Comments accepted to IJCAI 2025
Paradigms of AI Evaluation: Mapping Goals, Methodologies and Culture
机构 * Leverhulme Centre for the Future of Intelligence, University of Cambridge（未来智能研究所，剑桥大学） ； VRAIN, Universitat Politècnica de València（VRAIN，巴塞罗那理工大学）
Comments Accepted at IJCAI 2025 Survey Track
Deconfounding Multi-Cause Latent Confounders: A Factor-Model Approach to Climate Model Bias Correction
机构 * University of South Australia（南澳大利亚大学） ； CSIRO Environment（澳大利亚环境局） ； CSIRO Data61（澳大利亚数据61研究院）
Comments IJCAI 2025 Accepted
Self-Predictive Dynamics for Generalization of Vision-based Reinforcement Learning
机构 * Sungkyunkwan University（顺天乡大学）
Comments IJCAI 2022
Beyond Winning Strategies: Admissible and Admissible Winning Strategies for Quantitative Reachability Games
机构 * University of Colorado at Boulder（科罗拉多大学波德摩尔分校）
Comments Accepted to IJCAI 25
ADFormer: Aggregation Differential Transformer for Passenger Demand Forecasting
机构 * East China Normal University（东华大学） ； Aalborg University（奥尔堡大学） ； INSPUR Co.,Ltd（英伟达公司） ； KLATASDS-MOE
Comments 9 pages, 5 figures, 3 tables. IJCAI-2025
MIRROR: Multi-agent Intra- and Inter-Reflection for Optimized Reasoning in Tool Learning
Comments Accepted to 34rd International Joint Conference on Artificial Intelligence (IJCAI 2025)
DECASTE: Unveiling Caste Stereotypes in Large Language Models through Multi-Dimensional Bias Analysis
机构 * IBM Research, San Jose, CA, USA（IBM研究院，美国加利福尼亚州圣何塞） ； Dartmouth College, Hanover, NH, USA（达特茅斯学院，美国新罕布什尔州汉诺威） ； IBM Research, Hursley, Winchester, UK（IBM研究院，英国赫里福德郡温切斯特） ； IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA（IBM托马斯·J·沃森研究中心，美国纽约州亚当斯） ； IBM Research, Sao Paulo, Brazil（IBM研究院，巴西圣保罗）
Comments 7 (content pages) + 2 (reference pages) + 5 (Appendix pages), 5 figures, 6 Tables, IJCAI 2025
Knowledge-Informed Deep Learning for Irrigation Type Mapping from Remote Sensing
机构 * Dept. of Computer Science, University of Virginia（弗吉尼亚大学计算机科学系） ； Biocomplexity Institute, University of Virginia（弗吉尼亚大学生物复杂性研究所） ； US Department of Agriculture（美国农业部）
Comments Full version of the paper will be appearing at the Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence (IJCAI-25), Special Track on AI for Good
Revisiting Neural Networks for Continual Learning: An Architectural Perspective
机构 * Sichuan University（四川大学） ； Tsinghua University（清华大学） ； Zhejiang University（浙江大学）
Journal ref Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence. 2024: 4651-4659
Multi-granularity Knowledge Transfer for Continual Reinforcement Learning
机构 * Southwestern University of Finance and Economics（西南财经大学） ； Shanxi University（山西大学）
Comments the 34th International Joint Conference on Artificial Intelligence (IJCAI 2025)
Accurate Sublayer Pruning for Large Language Models by Exploiting Latency and Tunability Information
机构 * Seoul National University（首尔国立大学） ； LG AI Research（LG AI研究院）
Comments IJCAI 2025 Main Track
OpenCarbon: A Contrastive Learning-based Cross-Modality Neural Approach for High-Resolution Carbon Emission Prediction Using Open Data
机构 * Tsinghua University（清华大学）
Comments Accepted by IJCAI 2025
Multi-Source Collaborative Style Augmentation and Domain-Invariant Learning for Federated Domain Generalization
机构 * College of Intelligence and Computing, Tianjin University（智能与计算学院，天津大学）
Comments IJCAI 2025
Exploring the Trade-Offs: Quantization Methods, Task Difficulty, and Model Size in Large Language Models From Edge to Giant
Comments Accepted in IJCAI 2025, 21 pages, 2 figure
EPIC: Graph Augmentation with Edit Path Interpolation via Learnable Cost
机构 * Graduate School of Artificial Intelligence, POSTECH, South Korea（人工智能研究生院，POSTECH，韩国） ； Department of Computer Science & Engineering, POSTECH, South Korea（计算机科学与工程系，POSTECH，韩国）
Comments Accepted by IJCAI 2024
Point Cloud Mixture-of-Domain-Experts Model for 3D Self-supervised Learning
机构 * Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院，清华大学） ； Institute of Perceptual Intelligence, Pengcheng Laboratory（感知智能研究院，鹏城实验室） ； College of Computer Science and Software Engineering, Shenzhen University（深圳大学计算机科学与软件工程学院） ； Harbin Institute of Technology, Shenzhen（哈尔滨工业大学深圳学院）
Comments Accepted to IJCAI 2025
LLMs can Find Mathematical Reasoning Mistakes by Pedagogical Chain-of-Thought
机构 * Shanghai Business School（上海商学院） ； Learnable.AI Inc.（Learnable.AI公司） ； Centre for Frontier AI Research, A*STAR（前沿人工智能研究中心，A*STAR） ； Institute of High-Performance Computing, A*STAR（高性能计算研究所，A*STAR） ； The Hong Kong Polytechnic University（香港理工大学） ； Microsoft Research Asia（微软亚洲研究院）
Comments Accepted by IJCAI 2024
VRD-IU: Lessons from Visually Rich Document Intelligence and Understanding
机构 * The University of Melbourne（墨尔本大学） ； The University of Sydney（悉尼大学）
Comments Accepted at IJCAI 2025 Demonstrations Track
A Dynamic Stiefel Graph Neural Network for Efficient Spatio-Temporal Time Series Forecasting
机构 * School of Mathematics and Statistics, Wuhan University of Technology（武汉理工大学数学与统计学院）
Comments Accepted at IJCAI 2025
M3ANet: Multi-scale and Multi-Modal Alignment Network for Brain-Assisted Target Speaker Extraction
机构 * School of Computer Science and Technology, Anhui University（安徽大学计算机科学与技术学院） ； Alibaba group（阿里巴巴集团） ； Department of Automation, Tsinghua University（清华大学自动化系） ； Beijing National Research Center for lnformation Science and Technology, Tsinghua University（清华大学信息科学与技术国家研究中心）
Comments Accepted to IJCAI 2025
RenderBender: A Survey on Adversarial Attacks Using Differentiable Rendering
机构 * Georgia Tech（佐治亚理工学院） ； Technology Innovation Institute（技术创新研究所）
Comments 9 pages, 1 figure, 2 tables, IJCAI '25 Survey Track
Towards Automatic Sampling of User Behaviors for Sequential Recommender Systems
Comments IJCAI 2025
Causal-aware Large Language Models: Enhancing Decision-Making Through Learning, Adapting and Acting
机构 * School of Computer Science, Guangdong University of Technology（广东技术大学计算机科学学院） ； College of Mathematics and Computer Science, Shantou University（汕头大学数学与计算机科学学院） ； Huawei Noah’s Ark Lab, Huawei（华为诺亚实验室） ； Peng Cheng Laboratory, Shenzhen, China（鹏城实验室）
Comments Accepted by IJCAI 2025
A Comprehensive Survey on Physical Risk Control in the Era of Foundation Model-enabled Robotics
机构 * The University of Tokyo（东京大学） ； Japan AI Safety Institute（日本人工智能安全研究所）
Comments Accepted to IJCAI 2025 Survey Track
Image Captioning Evaluation in the Age of Multimodal LLMs: Challenges and Future Perspectives
机构 * University of Modena and Reggio Emilia（摩德纳和雷吉奥艾米利亚大学） ； IIT-CNR（意大利国家研究委员会IIT）
Comments IJCAI 2025. Repo GitHub: https://github.com/aimagelab/awesome-captioning-evaluation
Large Language Model Meets Constraint Propagation
机构 * Université Côte d’Azur（法国南海岸大学） ； CNRS（法国国家科学研究中心） ； I3S（信息科学与系统研究所）
Comments To appear in the Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence (IJCAI 2025)
