SUBMIT ONLINE: https://www.easychair.org/conferences/?conf=prai2026  (Please choose Special Session 6)

The booming of multimodal large models (MLLMs) has significantly enhanced the ability of machines to perceive and understand complex multi-source information (text, image, audio, video). Integrating MLLMs with intelligent recommendation systems breaks through the limitations of traditional single-modal recommendation, enabling more accurate user demand mining and personalized content delivery. However, key challenges remain, such as cross-modal semantic alignment, efficient feature fusion, and real-time recommendation adaptation. This session focuses on the cutting-edge intersection of MLLM perception understanding and intelligent recommendation, aiming to build an academic exchange platform for global experts to share latest achievements, explore innovative solutions, and promote the integration of technologies to advance the development of intelligent recommendation systems.

Chair:

Siling Feng, Hainan University, China Email: fengsiling@hainanu.edu.cn

 

RELATED TOPICS
Topics of interest include, but are not limited to:

•  Fundamental Theories of Multimodal Large Model Perception and Understanding
   MLLM-Driven Intelligent Recommendation Technologies
   Practical Applications of MLLM-Based Intelligent Recommendation
   Evaluation, Optimization and Security
   Emerging Trends and Cross-Disciplinary Integration
   Multimodal User Profiling and Preference Modeling
  
  

Invited Speakers

Asst. Prof. Julie Anne Angeles-Crystal, National University - Manila, Philippines

Julie Anne Angeles Crystal is the Internship and Linkages Coordinator of the College of Computing and Information Technologies at National University, Philippines. She is a Doctor of Information Technology candidate currently completing the final defense stage of her doctoral program. She holds a Master’s degree in Information Technology and a Bachelor of Science degree in Computer Science. She has more than two decades of combined experience in information technology, higher education, professional training, software development, quality assurance, and project management. She has earned several Microsoft professional certifications, including Microsoft Certified Trainer, Microsoft Certified Application Developer for .NET, Microsoft Certified Technology Specialist, Microsoft Certified Professional Developer, and Microsoft Certified Professional. Throughout her professional career, she has delivered technical training in Microsoft .NET technologies, C#, Visual Basic .NET, ASP.NET, web application development, database technologies, HTML5, JavaScript, CSS3, and Microsoft SQL Server. She has also organized and facilitated intensive software development boot camps for junior developers and industry professionals. Her previous industry experience includes serving as a project manager, software quality assurance specialist, and junior programmer, providing her with practical knowledge of the software development life cycle, client requirements analysis, application testing, project coordination, and technical implementation. As an educator and academic coordinator, her professional interests include artificial intelligence in education, work-integrated learning, internship readiness, graduate employability, responsible technology adoption, data-driven decision support, and university–industry collaboration. Her work focuses on strengthening the connection between academic preparation, professional competencies, student development, and evolving industry requirements. Title: From Classroom to Career: A Human-Centered AI Framework for Internship Readiness, Skills Matching, and Industry Linkages Abstract: The transition from university education to the workplace often depends on fragmented student records, manually reviewed résumés, generalized career preparation activities, and placement decisions that may not fully capture the competencies, interests, and development needs of individual students. These challenges are particularly evident in internship programs, where universities must simultaneously address student readiness, industry requirements, placement suitability, monitoring, and continuous program improvement. This invited talk proposes a human-centered artificial intelligence framework for supporting internship readiness, skills matching, and university–industry linkages. The framework combines natural language processing for extracting competencies from student résumés, portfolios, academic records, and internship descriptions; semantic matching for identifying suitable internship opportunities; skills-gap analysis for generating personalized development recommendations; generative AI for résumé enhancement and interview preparation; and employer feedback analytics for informing curriculum and internship program improvement. Rather than replacing internship coordinators, faculty members, or industry supervisors, the proposed framework positions artificial intelligence as a decision-support mechanism. It emphasizes informed consent, data privacy, explainability, fairness, human validation, and opportunities for students to review or challenge automated recommendations. The presentation offers a practice-informed conceptual architecture, an illustrative decision workflow, responsible AI safeguards, and a phased implementation roadmap for higher education institutions. It argues that the value of artificial intelligence in internship programs should not be measured solely by faster placement, but by its ability to produce more transparent, developmental, inclusive, and meaningful pathways from classroom learning to professional practice.