[1] His current focus is developing machine perception technologies, sensors, displays, and compute architectures for the next generation of augmented (AR), mixed (MR) and virtual reality (VR) systems.

His research has focused on using physical modeling and advanced statistical methods including artificial intelligence and machine learning to extract information from very large multi-wavelength (hyper-spectral) data sets.

[4] In his Ph.D. thesis, he focused on measuring the growth of structure and history of star formation in the universe using several data sets including the GOODS survey.

He subsequently led the development of new technique based on manifold learning that significantly reduced the number of observations required to calibrate photometric redshifts for dark energy measurements.

[13][14] Capak has also worked on improving galaxy modeling techniques using more advanced statistical methods and machine learning[15][16][17] including leading the development of the fitting pipeline for the SPHEREx mission.