Topics

AI and Multimodal Services have been driving Internet innovations and transforming traditional businesses. AIMS 2026 covers the following key areas:

Key Areas for AI, Especially Generative AI

    Generative AI Models: Development and application of generative models such as GANs (Generative Adversarial Networks), VAEs (Variational Autoencoders), and transformer-based models for creating synthetic data, images, text, and more.
    Creative AI: Leveraging generative AI for creative processes in art, music, and content generation, pushing the boundaries of creativity through machine learning.
    Automated Content Generation: Utilizing AI to generate text, images, videos, and other media content automatically, enhancing productivity and enabling new forms of content creation.
    AI-Driven Personalization: Implementing generative AI to create personalized experiences for users in various applications, including marketing, entertainment, and education.
    Ethical and Responsible AI: Addressing the ethical implications of generative AI, ensuring fairness, transparency, and accountability in AI-generated content and applications.
    Key Areas for Multimodal Services
    Multimodal Interaction and User Interfaces: Focuses on the integration of various interaction modes, such as voice, text, video, and gestures, to create seamless user experiences. It also explores advanced interfaces, including augmented and virtual reality.
    Multimodal Machine Learning: Investigates techniques for combining different data modalities for improved decision-making and developing deep learning models tailored for multimodal applications.
    Natural Language Processing (NLP) for Multimodal Services: Enhances conversational agents that understand and respond to multiple forms of input, and improves machine translation with integrated text, speech, and visual data.
    Multimodal Content Creation and Management: Develops platforms for creating and managing content across different media types, and enhances user engagement through personalized and adaptive multimedia content.
    Human-Computer Interaction (HCI) in Multimodal Systems: Crafts adaptive interfaces that respond to user preferences and behaviors, and evaluates the effectiveness and ease of use of multimodal applications.
    Multimodal Data Integration and Analysis: Techniques for processing and analyzing multimodal data streams in real time and innovative methods for visualizing complex multimodal datasets.
    Security and Privacy in Multimodal Services: Develops secure communication methods for multimodal data and ensures user privacy while handling diverse data types.
    Applications of Multimodal Services: Utilizes multimodal data for monitoring, diagnostics, and treatment in healthcare, creates interactive and immersive learning environments in education, enhances gaming and virtual worlds in entertainment, and implements multimodal interactions in smart homes and cities.
    Emerging Trends in Multimodal Services: Explores advancements in AI technologies tailored for multimodal applications, new developments in sensors and hardware that support multimodal interactions, and the potential and challenges of multimodal services in various domains.
    Multimodal Service Platforms and Frameworks: Builds robust architectures for delivering multimodal services, develops middleware and APIs to support multimodal service integration, and leverages cloud and edge computing for scalable multimodal applications.
    Evaluation and Benchmarking of Multimodal Systems: Establishes metrics for evaluating the performance of multimodal systems, conducts studies to compare different multimodal interaction techniques, and engages in user studies to assess the usability and impact of multimodal applications.