Stanford EE292R AI and Data for Science | Autumn 2026 | From World Models to World Agents

For more information about Stanford’s graduate programs, visit: https://online.stanford.edu/graduate-education This lecture is from Stanford EE292R AI and Data for Science, and it covers recent advances in video world models, specifically focusing on enhancing temporal consistency and reasoning across long contexts, as well as mitigating auto-regressive drift, and explores the integration of multi-agent dynamics and the development of effective human-centric conditioning and control strategies. Follow the course schedule: https://aida4sci.stanford.edu/schedule.html#fall-2026 Speaker: Gord