Xudong Hong is a doctoral student at Universität des Saarlandes with over a decade of research and engineering experience at the intersection of computer science, linguistics, and cognitive science. He develops multimodal NLP and deep learning methods to extract prototypical event representations and model inner-event structures, aiming to generate semantically coherent and pragmatically informative stories from photo albums. Supervised by Vera Demberg, his work connects visual-language models and cognitive theories of commonsense acquisition across sensory modalities. Based in Saarbrücken, he blends rigorous academic training from South China University of Technology and Saarland University with hands-on experimentation in visually grounded story generation. His projects reveal a practical curiosity for how narrative comprehension and production emerge from multimodal signals—a perspective that informs both model design and evaluation.
11 years of coding experience
Master’s Degree, Master’s Degree at Universität des Saarlandes
Bachelor’s Degree, Bachelor’s Degree at South China University of Technology
English, German, Chinese, chinese (modern standard mandarin)
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.
Request Free Trial
Xudong Hong - Doctoral Student at Universität des Saarlandes