Published multiple papers in top conferences such as ICCV, ACM MM, ICLR, and journals like IEEE Transaction on Image Processing (TIP) and Journal of Electronic Imaging (JEI). His CVPR 2021 paper won the Scientific Paper Challenge organized by Dolby Australia.
Research Experience
Involved in various research projects related to audio-visual contextual and contrastive learning, guided text-to-video diffusion models, and personalization of text-to-image diffusion models. Published at CVPR 2021 and was part of the ORBITRON team that won the few-shot learning competition at the VizWiz workshop.
Education
Earned his Ph.D. in 2022 (specific school and advisor information not provided).
Background
Grew up in Indonesia with a love for its people and cultures. Currently, he is a machine learning and audio-visual researcher focusing on multi-modal learning for discriminative and generative models, as well as meta-learning, life-long learning, and continual learning.
Miscellany
More information can be found via his Google Scholar profile.