SUBMIT ONLINE: https://www.easychair.org/conferences/?conf=prai2026  (Please choose Special Session 15)

This session convenes researchers to explore the dynamic intersection of Generative AI (GenAI), Computer Vision (CV), and Large Language Models (LLMs). We aim to foster discussion on advanced topics defining the next wave of intelligent systems. Key themes include the evolution of multimodal fusion, integrating diverse data types like visual (e.g., facial and tongue diagnostics) and textual information for sophisticated applications in healthcare management. Another core focus is controllable content generation, including novel techniques in painting-based image synthesis and style-decoupled editing. The workshop will also spotlight breakthroughs in cross-modal learning, examining how systems can achieve robust visual-language grounding for tasks like open-world segmentation. Finally, we explore the novel application of large models in specialized domains, from adapting Transformers for small object detection to developing LLMs for nuanced tasks like educational text critique and auxiliary diagnostics. This gathering will provide a critical platform for sharing insights and charting the future of integrated intelligent systems.

Chair:	Chair:	Chair:
Prof. Han-Cheng Hsiang Xiamen Institute of Technology, China Shc5443@gmail.com	Assoc. Prof. Moyu Wang Xiamen Institute of Technology, China wangmoyu@xit.edu.cn	Assoc. Prof. Yingjie Wang Xiamen Institute of Technology, China wangyingjie@xit.edu.cn

Topics of interest include, but are not limited to:

• Generative AI
• Large Language Models (LLMs)
• Computer Vision
• Multimodal Learning
• Interactive Image Generation
• AI in Healthcare
• Visual-Language Grounding
• Agricultural and urban applications