Rahul Ravishankar

I am an undergraduate at UC Berkeley studying Computer Science and am currently advised by Prof. Jitendra Malik at BAIR. I have also had the pleasure of working with Prof. Alvin Liu at Johns Hopkins University in collaboration with MSFT Applied Sciences on multimodal single-cell RNA-seq models.

Email  /  LinkedIn  /  Github  /  Google Scholar

Rahul Ravishankar
Research

My research interests are generally in deep learning (self-supervision, reasoning, scaling) and their applications to computer vision and embodied systems.
Scaling Properties of Diffusion Models For Perceptual Tasks
Rahul Ravishankar*, Zeeshan Patel*, Jathushan Rajasegaran, Jitendra Malik
project page / arXiv / code

We show how diffusion models benefit from scaling training and test-time compute for perceptual tasks and unify tasks such as depth estimation, optical flow, and amodal segmentation under the framework of image-to-image translation.
An Empirical Study of Autoregressive Pre-training from Videos
Jathushan Rajasegaran, Ilija Radosavovic, Rahul Ravishankar, Yossi Gandelsman, Christoph Feichtenhofer, Jitendra Malik
project page / arXiv / code [coming soon]

We trained LLaMA models up to 1 billion parameters on 1 trillion visual tokens. The resulting model can do diverse tasks including image and video recognition, video tracking, action prediction, and robotics. We also study the scaling properties of these family of models.
Teaching