AIETDS 2027

The AIETDS is a serial conference focusing on experimental, theoretical and applied innovations across Artificial Intelligence, Education Technology and Data Science. The conference strives to build an inclusive interdisciplinary platform, bringing together academic researchers, scholars and industrial specialists engaged in fundamental research, applied science and engineering technology to exchange cutting-edge discoveries and valuable insights.

We sincerely invite experts, scholars and industry practitioners from universities and research institutions worldwide to submit papers and join our academic communications. Topics of interest include, but are not limited to:

🔹 Track 1: AI Education Methods • Trustworthiness assurance mechanisms for generative educational content • Fine-tuning methodologies for multilingual large language models in educational settings • Multimodal fusion techniques for interdisciplinary education • Reinforcement learning applications in educational cognitive modeling • Personalized prompt engineering strategies for instructional design • Few-shot adaptation techniques for educational scenarios • Lightweight AI deployment frameworks for educational environments • Educational agents and multi-agent collaborative architectures • Autonomous reasoning and decision-making in educational agents • Generative AI-driven educational assessment and feedback systems • Large language model-powered personalized learning pathways • Full lifecycle management of educational foundation models • Teacher–student–machine collaborative knowledge creation • Construction of multimodal educational cognitive foundation models	🔹 Track 2: Educational Data Science • Causal inference frameworks for learning behavior analysis • Dynamic construction and application of educational knowledge graphs • Multimodal learning analytics pipelines • Modeling and prediction of educational time-series data • FERPA/GDPR-compliant data governance and differential privacy mechanisms • Visualization and explainability in educational big data • Real-time detection and feedback systems for learning behaviors • Federated learning for multi-source heterogeneous educational data • Multimodal Learning Analytics (MMLA) • Educational open datasets and reproducibility in data science research • Real-time analysis of educational time-series and streaming data • Dynamic modeling and intervention of classroom group engagement • Multimodal interaction analysis in synchronous classroom environments • Brain-computer interface-driven learning state monitoring

🔹 Track 3: Intelligent Education Systems • Neuroscience-inspired adaptive learning systems • Interoperability protocols for educational metaverse environments • Digital twin construction for teaching environments • Adversarial robustness testing for educational AI systems • Edge computing solutions for special education • Secure offloading mechanisms for educational AI • Educational robotics and embodied intelligence • Lightweight VR/AR teaching tools • Deployment and operational management of educational AI systems • Large language model-powered personalized learning pathways • Embodied intelligence and educational robot interaction • Educational digital twins and metaverse learning environments • Vertical foundation model applications in vocational education • Brain-computer interface and neurofeedback-based teaching interventions	🔹 Track 4: Governance of Educational AI • Bias detection frameworks for educational foundation models • Transparency assessment metrics for educational AI systems • SDG4 (Quality Education) relevance and impact analysis • Teacher–AI responsibility allocation frameworks • Quantitative assessment and pathways for AI education equity • Ethical auditing and compliance frameworks for AI educational products • AI dependency and risks of cognitive capability degradation • Dynamic human–AI responsibility allocation mechanisms • Human–AI collaborative teaching competence and teacher AI literacy • Access assessment and continuous monitoring of AI educational products • Data poisoning and model security in educational AI • AI-driven cyberbullying detection and intervention • Human–AI interaction and cognitive security mechanisms • Ethical governance of brain-computer interface applications in education

🔹 Track 5: Data Mining and Learning • Large-scale data mining and pattern discovery • Novel deep learning and representation learning architectures • Few-shot, zero-shot, and transfer learning methodologies • Explainability and fairness in data science • Reinforcement learning and decision intelligence • Anomaly detection and change point detection • Graph neural networks and knowledge graph reasoning • Causal inference and counterfactual reasoning in data analysis	🔹 Track 6: Data Engineering and Visualization • Data quality assessment and preprocessing techniques • Distributed data warehouses and data lake architectures • Real-time stream processing systems • Data visualization and interactive analytics • Privacy-preserving computing (federated learning, differential privacy, secure multi-party computation) • Data governance and metadata management • AI-synthetic data applications in educational research • AI-synthetic data generation and evaluation • Human–AI collaborative data exploration and interactive analytics • Digital-real integration and spatial computing applications