About

I am a Research Assistant at the Vision and AI Lab (VAL), Indian Institute of Science (IISc), Bangalore, advised by Prof. R. Venkatesh Babu. My research focuses on evaluating and improving the physical grounding of video generation models — particularly their ability to simulate real-world Newtonian dynamics. I am also broadly interested in multi-modal generation, editing, and personalization.

Before this, I was a Senior Engineer at Samsung R&D Institute India, Bangalore. I completed my MS (By Research) in Computer Science and Engineering from IIT Kanpur, advised by Prof. Gaurav Sharma, where my thesis work focused on audio-guided facial expression editing using StyleGAN.

Outside research, I enjoy playing guitar 🎸 and singing 🎵.

News

Publications · click cards to expand

Principia overview
Principia: Relational Physics Tests for Video Models
Under Review
Varun Varma Thozhiyoor*, Shivam Tripathi*, R. Venkatesh Babu, Anand Bhattad *Equal contribution
TL;DR Modern video generators fail surprisingly simple Newtonian physics tests. Principia uses calibration-independent relational constraints and finds no generator exceeds 0.5 physical consistency despite all scoring >0.7 on VBench.
arXiv (soon) Project (soon)
Click to expand
Objects in Generated Videos Are Slower Than They Appear
CVPR Findings 2026
Varun Varma Thozhiyoor, Shivam Tripathi, R. Venkatesh Babu, Anand Bhattad
TL;DR Video diffusion models exhibit "sub-Earth" gravity — objects fall up to 4× slower than physics dictates. A LoRA fine-tuned on just 100 clips raises effective gravity from 1.81 → 6.43 m/s² (65% of Earth's g).
Paper Project Page
Click to expand