I am Amir Habibian, research scientist (Director of Engineering) at Qualcomm AI Research. My research is focused on computational efficiency of computer vision models to process high resolution images and videos. Currently, I lead the Generative Vision group, which develops efficient diffusion models to generate images and videos on edge devices such as phone and XR headsets.

I received my PhD on learning multimodal video representations from the University of Amsterdam in 2016. During my studies, I received the Best Paper Award at ACM Multimedia 2014, the Best Paper Award at ASCI 2015, and top performer in the TRECVID video search challenge in 2014 and 2015.