Description
Instructor(s)/Supervisor(s)/Coordinator(s): Harry YANGThis course focuses on the emerging field of video generation, an intersection of computer vision, machine learning, and digital creativity. Students will explore state-of-the-art models and methodologies for generating, synthesizing, and editing videos using deep learning, including autoregressive transformers, diffusion models, and multimodal architectures. The course integrates theoretical understanding, hands-on experimentation, and creative applications, preparing students to contribute to next-generation visual AI systems for art, film, gaming, and interactive media.