Rohan Choudhury

I am a PhD Student at Carnegie Mellon University advised by Kris Kitani and Laszlo Jeni, where I work on efficient video understanding and tokenization.

During my PhD, I have spent time at Meta FAIR (with Jing Huang).

Before my PhD, I was a software engineer at Nuro, working on trajectory prediction models. Before then, I graduated from Caltech where I worked with Professor Yisong Yue.

Email  /  Google Scholar  /  Github

profile photo

Current Research

I'm currently interested in efficient video understnading PROVIDE MORE DETAILs.

Video Question Answering with Procedural Programs
Rohan Choudhury, Kris M. Kitani, Laszlo Jeni

ECCV, 2024
arXiv,
Don't Look Twice: Faster Video Transformers with Run-Length Tokenization
Rohan Choudhury*, Guanglei Zhu, Sihan Liu, Koichiro Niinuma, Kris M. Kitani, Laszlo Jeni
NeurIPS, 2024 (Spotlight)
arXiv,

This website uses this template.