Generative models can now produce realistic and diverse synthetic data in many domains. This makes them a viable choice as a data source for training downstream AI systems. Unlike real data, synthetic data can be steered and optimized via interventions in the generative process. I will share my view on how this makes synthetic data act like data++, data with additional capabilities. I will discuss the advantages and disadvantages of this setting, and show several applications toward problems in computer vision and robotics.
Phillip Isola Associate Professor, Department of Electrical Engineering and Computer Science
Generative Models as a Data Source for AI Systems
Panel Discussion: AI Generation - From Research to Impactful Use Cases
Digital Twin and AI: Shaping the Future of Real Estate
Technology and Inequality in the Age of AI
AI for Chemistry and Materials: Are We There Yet?