About Me

I am Rohit Kundu (he/him/his), a Ph.D. candidate at the University of California, Riverside working in the Vision and Learning Group headed by Prof. Amit K. Roy-Chowdhury.

My doctoral research is on leveraging Foundation Models for downstream tasks like image segmentation and media forensics, with a latest focus on generative AI models (particularly video generation models). I primarily code in Python and use the JAX, PyTorch, Keras, and TensorFlow libraries for deep learning and have published several papers in reputed peer-reviewed journals and conferences (Google Scholar). I am also a regular reviewer for CVPR, ECCV, ICCV, ICASSP, and other notable IEEE, Elsevier, Springer and Wiley journals.

I have had the opportunity to work in the following institutions: