Multi-scale Artificial Intelligence (MAI) refers to an approach in artificial intelligence that involves the integration of models and techniques across multiple scales. This approach enables AI systems to handle and analyze data at different levels of detail and resolution, from the microscopic to the macroscopic.

By using multi-scale representations, MAI can capture information at various levels of granularity, allowing for more comprehensive and accurate analysis. This technique is especially useful in fields like computer vision, where it can help in tasks such as image recognition, object detection, and scene understanding.

In essence, MAI combines the strengths of different AI techniques and models to work together at multiple scales, providing a more comprehensive understanding of complex systems and data. This approach can enhance the performance and accuracy of AI systems in various applications.

MAI 2026 welcomes submissions reporting research that advances artificial intelligence, broadly conceived. Original papers are invited to submit to the following Track areas:

Track 1: Foundations of Artificial Intelligence

Machine Learning, Natural Language Processing, Large Language Models, Neural Networks and Deep Learning, Computer Vision, Data Mining, Deep Learning Architectures (Transformers/CNNs/RNNs Evolution), Reinforcement Learning & Multi-agent Systems, Explainable & trustworthy AI, Federated & Distributed Learning, Neuro-symbolic Hybrid Systems, Meta-learning & Adaptive Algorithms, Graph Neural Networks & Knowledge Representation, Online & Continual Learning, Multimodal Fusion Techniques, Causal Reasoning & Logical Learning, Multiagent Systems, Knowledge Representation, Human-in-the-loop AI, Robotics and Perception

Track 2: Applications of Artificial Intelligence

AI Applications in Healthcare and Medicine, AI Applications in Education, AI Applications in Finance, AI Applications in Smart Cities and Transportation, AI Applications in Aerospace, AI Applications in Engineering and Manufacturing, AI Applications in Business Intelligence, AI in Robotics and Autonomous Systems, AI in Smart Cities and Urban Computing, AI for Internet of Things, AI in Education and E-learning

Track 3: Multi-scale Artificial Intelligence and Applications

Multi-scale Representation Learning in Artificial Intelligence, Multi-scale Object Detection and Recognition in Computer Vision, Multi-scale Artificial Intelligence for Big Data Analysis, Multi-scale Artificial Intelligence in Healthcare, Multi-scale Artificial Intelligence for Smart Cities, Scalable Machine Learning Techniques for Multi-scale Data Analysis, Cross-scale AI in Decision Support Systems

Track 4: Societal Impact & Emerging Frontiers

AI ethics & governance frameworks, Privacy-preserving machine learning, Digital content authentication, Human-AI collaboration & cognitive augmentation, Brain-computer interfaces & neuro-AI, Affective computing & mental health, AI-assisted scientific discovery, Sustainable AI (green computing/carbon footprint), AI policy & legal studies, Virtual human technologies, Multimodal human-computer interaction, AI for art & creative generation, Open-source ecosystems & toolchains, AI education & talent development