My name is Jason and I research multimodal machine learning and embodied AI at the University of Zurich.
Prior to UZH, I conducted research on multimodal machine learning at the University of Bonn and worked in digital product development teams at the BBC and Disney on digital video services, games, and mobile apps. My academic background is in cogniton and computation (University of London, Birkbeck), data science (University of Stirling), and machine learning (UC San Diego).
Right now, I am working on developing learning methods and resources to train artificial agents in virtual environments. Specific areas of interest are the representation of time in tasks and data, sequence modeling methods for multimodal data, and extending cross-disciplinary links between machine learning and computational cognitive neuroscience.
- A Priority Map for Vision-and-Language Navigation with Trajectory Plans and Feature-Location CuesIn 2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2023