September 2025, published a paper on Simplifying Knowledge Transfer in Pretrained Models at TMLR; July 2025, gave a talk titled The Sound Dimension: Speech and Audio in Multimodal AI at CVIT workshop 2025; June 2025, received best paper award at FGVC workshop at CVPR 2025; May 2025, successfully mentored Kawshik to defend his thesis and complete his Dual Degree, who is now moving on to Google DeepMind.
Research Experience
Presently an associate professor at IIIT Hyderabad, mentoring students and involved in various research projects. Conducted master's thesis work at INRIA and continued there for PhD.
Education
PhD: INRIA Rhone Alpes/University of Grenoble, Applied Mathematics and Computer Science, under the guidance of Remi Ronfard; Master's: Completed with Erasmus Mundus scholarship under CIMET consortium, spent a semester each in Spain, Norway, and France; Bachelor's: Indian Institute of Information Technology, Design and Manufacturing (IIITDM) Jabalpur, India, first batch of the institute.
Background
Currently an associate professor at IIIT Hyderabad, affiliated with the Center for Visual Information Technology (CVIT). Also advising a beautiful animation startup on their AI and ML related efforts, Animaker.com. Research interests lie in applied machine learning for applications in computer vision and multimedia, including computational videography/cinematography, image/video editing, multiple sensor fusion for 3D analytics, sports analytics, document analytics, and visual detection, tracking, and recognition.
Miscellany
Personal interests include spending time with family, playing cards, going on bicycle rides, reading ancient literature, and exploring mountains.