Associate Professor Dong Wang will present the keynote at the second workshop on generative AI for recommender systems and personalization on August 4, in Toronto, Canada. The event will be held in conjunction with KDD 2025.
For his keynote, "Harnessing Generative AI for Efficient Multimodal Recommender Systems and Privacy-preserving Personalized Image Generation," Wang will explore how emerging AI models like large language models, diffusion networks, and multimodal architectures are transforming fields from recommender systems to healthcare. Wang will highlight two strands of recent work: PRIME, a framework that uses LLM-based feedback for more efficient, multimodal recommendations; and the Anti-Tamper Perturbation (ATP) scheme, a privacy-focused approach to personalized image generation that protects images from tampering.
Wang's research interests lie in the area of social sensing, intelligence and computing, human-centered AI, and big data analytics. His work has been applied in a wide range of real-world applications such as social network analysis, crowdsourcing, disaster response, education, smart cities, synthetic biology, and environmental sustainability.