I am currently a Research Assistant at the Vision and AI Lab (VAL), Indian Institute of Science (IISc), Bangalore, where I work under the supervision of Prof. Venkatesh Babu. My current research focuses on evaluating and improving the physical grounding of foundation video models. I am also interested in multi-modal generation, editing, and personalization. Previously, I worked as a Senior Engineer at Samsung R&D Institute India, Bangalore. I completed my MS (By Research) in Computer Science and Engineering from Indian Institute of Technology, Kanpur (IIT Kanpur), and my undergraduate studies in Computer Science from PSIT Kanpur. Outside research, I enjoy playing guitar and singing. For more details, please see my CV.

News

  • [Mar 2026] Our paper Objects in Generated Videos Are Slower Than They Appear was accepted to CVPR 2026 Findings.
  • [May 2025] Joined the Vision and AI Lab (VAL), IISc Bangalore as a Research Assistant under Prof. R. Venkatesh Babu.
  • [July 2024] Joined Samsung R&D Institute Bangalore as Senior Engineer (Research).

Publications

Principia: Relational Physics Tests for Video Models

(under review)

Varun Varma Thozhiyoor, Shivam Tripathi, R. Venkatesh Babu, Anand Bhattad

arXiv (soon) | Project Page (soon)

Objects in Generated Videos Are Slower Than They Appear

CVPR Findings 2026

Varun Varma Thozhiyoor, Shivam Tripathi, R. Venkatesh Babu, Anand Bhattad

Paper | Project Page