ISTD PhD Oral Defence Seminar by Mark He Huang – Modern AI systems often struggle in physical environments where observations are incomplete, noisy and constantly changing. This seminar presents a feedback-guided representation learning framework that helps AI systems revise what they know, maintain useful representations over time and generate physically plausible outcomes. The work spans machine unlearning, object-centric 3D visual memory and simulator-guided video generation, with the broader aim of enabling more reliable reasoning in the dynamic physical world.
