IJCAI

MS-DPPs: Multi-Source Determinantal Point Processes for Contextual Diversity Refinement of Composite Attributes in Text to Image Retrieval

Naoya Sogi, Takashi Shibata, Makoto Terao, Masanori Suganuma, Takayuki Okatani

机构 * Visual Intelligence Research Laboratories, NEC Corporation（NEC公司视觉智能研究实验室） ； Graduate School of Information Sciences, Tohoku University（东北大学信息科学研究生院） ； RIKEN Center for AIP（理化学研究所AIP研究中心） 纠错

Comments IJCAI 2025. Code: https://github.com/NEC-N-SOGI/msdpp

Q-Detection: A Quantum-Classical Hybrid Poisoning Attack Detection Method

Haoqi He, Xiaokai Lin, Jiancai Chen, Yan Xiao

机构 * School of Cyber Science and Technology, Shenzhen Campus of Sun Yat-sen University（中山大学计算机科学与技术学院（深圳校区）） 纠错

Comments IJCAI 2025 Main Conference Accepted Paper

Many-Task Federated Fine-Tuning via Unified Task Vectors

Vasileios Tsouvalas, Tanir Ozcelebi, Nirvana Meratnia

机构 * Eindhoven University of Technology（埃因霍温理工大学） 纠错

Comments 10 pages, 6 figures, accepted in FedGenAI-IJCAI 2025

Fine-tuning Multimodal Transformers on Edge: A Parallel Split Learning Approach

Timo Fudala, Vasileios Tsouvalas, Nirvana Meratnia

机构 * Eindhoven University of Technology（埃因霍温理工大学） 纠错

Comments 10 pages, 5 figures, accepted to FedGenAI-IJCAI 2025

CodeMirage: Hallucinations in Code Generated by Large Language Models

Vibhor Agarwal, Yulong Pei, Salwa Alamir, Xiaomo Liu

机构 * University of Surrey（萨里大学） ； JP Morgan AI Research（摩根大通AI研究） 纠错

Comments Accepted at AutoMates @ IJCAI 2024

Prompt-Free Conditional Diffusion for Multi-object Image Augmentation

Haoyu Wang, Lei Zhang, Wei Wei, Chen Ding, Yanning Zhang

机构 * Northwestern Polytechnical University（西北工业大学） ； Xi’an University of Posts & Telecommunications（西安邮电大学） 纠错

Comments Accepted at IJCAI 2025

From General Relation Patterns to Task-Specific Decision-Making in Continual Multi-Agent Coordination

Chang Yao, Youfang Lin, Shoucheng Song, Hao Wu, Yuqing Ma, Shang Han, Kai Lv

Comments IJCAI 2025 Accepted

City-Level Foreign Direct Investment Prediction with Tabular Learning on Judicial Data

Tianxing Wu, Lizhe Cao, Shuang Wang, Jiming Wang, Shutong Zhu, Yerong Wu, Yuqing Feng

机构 * School of Computer Science and Engineering, Southeast University, Nanjing, China（东南大学计算机科学与工程学院） ； Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education, China（新一代人工智能技术及其交叉应用关键实验室（东南大学）） ； School of Law, Southeast University, Nanjing, China（东南大学法学院） 纠错

Comments 9 pages, accepted by IJCAI 2025

SOSAE: Self-Organizing Sparse AutoEncoder

Sarthak Ketanbhai Modi, Zi Pong Lim, Yushi Cao, Yupeng Cheng, Yon Shin Teo, Shang-Wei Lin

机构 * Nanyang Technological University（南洋理工大学） ； Continental Automotive Singapore 纠错

Comments Accepted at IJCAI-DSO Workshop 2024

ARMR: Adaptively Responsive Network for Medication Recommendation

Feiyue Wu, Tianxing Wu, Shenqi Jing

机构 * School of Computer Science and Engineering, Southeast University, Nanjing, China（东南大学计算机科学与工程学院） ； Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education, China（新一代人工智能技术及其交叉应用关键实验室（东南大学）） ； The First Affiliated Hospital with Nanjing Medical University (JiangSu Province Hospital), Nanjing, China（南京医科大学第一附属医院（江苏省人民医院）） 纠错

Comments 9 pages, accepted by IJCAI 2025

Answer Set Programming Modulo Theories and Reasoning about Continuous Changes

Joohyung Lee, Yunsong Meng

机构 * School of Computing, Informatics and Decision Systems Engineering（计算、信息与决策系统工程学院） ； Arizona State University（亚利桑那州立大学） 纠错

Comments In Proceedings of the 23rd International Joint Conference on Artificial Intelligence (IJCAI 2013), pages 990-996, 2013

Consistency-Aware Padding for Incomplete Multi-Modal Alignment Clustering Based on Self-Repellent Greedy Anchor Search

Shubin Ma, Liang Zhao, Mingdong Lu, Yifan Guo, Bo Xu

机构 * School of Software Technology, Dalian University of Technology（大连理工大学软件学院） 纠错

Comments Accepted at IJCAI 2025. 9 pages, 3 figures

In-Context Meta LoRA Generation

Yihua Shao, Minxi Yan, Yang Liu, Siyu Chen, Wenjie Chen, Xinwei Long, Ziyang Yan, Lei Li, Chenyu Zhang, Nicu Sebe, Hao Tang, Yan Wang, Hao Zhao, Mengzhu Wang, Jingcai Guo

机构 * The Hong Kong Polytechnic University（香港理工大学） ； Tsinghua University（清华大学） ； Beijing Institute for General Artificial Intelligence (BIGAI)（北京通用人工智能研究院） ； University of Trento（特伦托大学） ； University of Copenhagen（哥本哈根大学） ； Peking University（北京大学） 纠错

Comments Accepted by IJCAI 2025

Spotlighting Partially Visible Cinematic Language for Video-to-Audio Generation via Self-distillation

Feizhen Huang, Yu Wu, Yutian Lin, Bo Du

机构 * School of Computer Science, Wuhan University（武汉大学计算机学院） 纠错

Comments Accepted by IJCAI 2025

Agent Ideate: A Framework for Product Idea Generation from Patents Using Agentic AI

Gopichand Kanumolu, Ashok Urlana, Charaka Vinayak Kumar, Bala Mallikarjunarao Garlapati

机构 * TCS Research, Hyderabad, India（塔塔咨询服务研究中心，印度海得拉巴） ； IIIT Hyderabad（IIIT海得拉巴） 纠错

Comments AgentScen Workshop, IJCAI 2025

Non-collective Calibrating Strategy for Time Series Forecasting

Bin Wang, Yongqi Han, Minbo Ma, Tianrui Li, Junbo Zhang, Feng Hong, Yanwei Yu

机构 * Ocean University of China（中国海洋大学） ； Southwest Jiaotong University（西南交通大学） ； JD Intelligent Cities Research（京东智能城市研究院） ； JD iCity, JD Technology, China（京东i城，京东科技，中国） ； Beijing Key Laboratory of Traffic Data Mining and Embodied Intelligence（北京交通数据挖掘与具身智能重点实验室） 纠错

Comments Accepted by IJCAI 2025

A Review on Zeroing Neural Networks

Chengze Jiang, Jie Gui, Long Jin, Shuai Li

Comments This is what we submitted to IJCAI 2023. Maybe we will update this paper in the future

Grounding Creativity in Physics: A Brief Survey of Physical Priors in AIGC

Siwei Meng, Yawei Luo, Ping Liu

Comments Accepted by IJCAI 2025 Survey Track

METEOR: Melody-aware Texture-controllable Symbolic Orchestral Music Generation via Transformer VAE

Dinh-Viet-Toan Le, Yi-Hsuan Yang

机构 * Univ. Lille, CNRS, Inria, Centrale Lille, UMR 9189 CRIStAL（里尔大学、法国国家科学研究中心、法国国家信息与自动化研究所、里尔中央理工大学、UMR 9189 CRIStAL） ； National Taiwan University（台湾国立台湾大学） 纠错

Comments Accepted to 34rd International Joint Conference on Artificial Intelligence (IJCAI 2025) - AI, Arts and Creativity Special Track. Demo: https://dinhviettoanle.github.io/meteor

Exploring Semantic Masked Autoencoder for Self-supervised Point Cloud Understanding

Yixin Zha, Chuxin Wang, Wenfei Yang, Tianzhu Zhang

机构 * University of Science and Technology of China（中国科学技术大学） ； Deep Space Exploration Lab（深空探测实验室） 纠错

Comments Accepted by IJCAI 2025

Dual-Perspective United Transformer for Object Segmentation in Optical Remote Sensing Images

Yanguang Sun, Jiexi Yan, Jianjun Qian, Chunyan Xu, Jian Yang, Lei Luo

机构 * PCA Lab, Nanjing University of Science and Technology（南京理工大学光电信息科学与工程学院） ； School of Computer Science and Technology, Xidian University（西安电子科技大学计算机科学与技术学院） 纠错

Comments Accepted by IJCAI 2025

StarFT: Robust Fine-tuning of Zero-shot Models via Spuriosity Alignment

Younghyun Kim, Jongheon Jeong, Sangkyung Kwak, Kyungmin Lee, Juho Lee, Jinwoo Shin

机构 * Samsung（三星） ； Korea University（韩国大学） ； General Robotics（通用机器人） ； KAIST（韩国科学技术院） 纠错

Comments IJCAI 2025; Code is available at https://github.com/alinlab/StarFT

Beyond Fixed Length: Bucket Pre-training is All You Need

Qing Yang, Qiyao Peng, Hongtao Liu, Kai Liu, Bing Qin, Ting Liu

机构 * Harbin Institute of Technology（哈尔滨工业大学） ； Du Xiaoman Financial Technology（杜晓曼金融科技） ； Tianjin University（天津大学） 纠错

Comments 8 pages, 5 figures, 3 tables. Accetped by IJCAI 2025

Antibody Design and Optimization with Multi-scale Equivariant Graph Diffusion Models for Accurate Complex Antigen Binding

Jiameng Chen, Xiantao Cai, Jia Wu, Wenbin Hu

机构 * School of Computer Science, Wuhan University, Wuhan, China（武汉大学计算机学院） ； Department of Computing, Macquarie University, Sydney, Australia（麦考瑞大学计算机系） ； Wuhan University Shenzhen Research Institute, Shenzhen, China（武汉大学深圳研究院） 纠错

Comments 9 pages, 4 figures, accepted at IJCAI 2025

COLUR: Confidence-Oriented Learning, Unlearning and Relearning with Noisy-Label Data for Model Restoration and Refinement

Zhihao Sui, Liang Hu, Jian Cao, Usman Naseem, Zhongyuan Lai, Qi Zhang

机构 * Shanghai Jiao Tong University（上海交通大学） ； Tongji University（同济大学） ； Macquarie University（麦考瑞大学） ； Shanghai Ballsnow Intelligent Technology Co. Ltd（上海Ballsnov智能技术有限公司） 纠错

Comments IJCAI 2025

Recalling The Forgotten Class Memberships: Unlearned Models Can Be Noisy Labelers to Leak Privacy

Zhihao Sui, Liang Hu, Jian Cao, Dora D. Liu, Usman Naseem, Zhongyuan Lai, Qi Zhang

机构 * Shanghai Jiao Tong University（上海交通大学） ； Tongji University（同济大学） ； Macquarie University（麦考瑞大学） ； Shanghai Ballsnow Intelligent Technology Co. Ltd（上海Ballsnow智能科技有限公司） 纠错

Comments IJCAI 2025

Probing the Embedding Space of Transformers via Minimal Token Perturbations

Eddie Conti, Alejandro Astruc, Alvaro Parafita, Axel Brando

机构 * TAIES Group, HPES Lab, Barcelona Supercomputing Center (BSC)（TAIES小组、HPES实验室、巴塞罗那超级计算中心） 纠错

Comments IJCAI 2025 Workshop on Explainable Artificial Intelligence

Cause-Effect Driven Optimization for Robust Medical Visual Question Answering with Language Biases

Huanjia Zhu, Yishu Liu, Xiaozhao Fang, Guangming Lu, Bingzhi Chen

机构 * Beijing Institute of Technology（北京理工大学） ； Harbin Institute of Technology（哈尔滨工业大学） ； Guangdong University of Technology（广东工业大学） 纠错

Comments Accepted at IJCAI 2025

Reflective Verbal Reward Design for Pluralistic Alignment

Carter Blair, Kate Larson, Edith Law

机构 * University of Waterloo（滑铁卢大学） 纠错

Comments 9 pages, 3 figures, accepted to the IJCAI 2025 Human-Centred AI track. Project repository at: https://osf.io/8yxf2/

Human Action CLIPs: Detecting AI-generated Human Motion

Matyas Bohacek, Hany Farid

机构 * Google（谷歌） ； Stanford University（斯坦福大学） ； University of California, Berkeley（加州大学伯克利分校） 纠错

Journal ref Workshop on Deepfake Detection, Localization and Interpretability @ IJCAI 2025