I come from a family of folk theatre artistes, brought up in the beautiful north-east, at the borders of India. As a theatre artist when I was a child, and as a researcher when I was an adult, I travelled the length and breadth of the country. One picks up a few good stories along the way.
Lately I have been fascinated by the fact that it appears large-scale pretraining makes robust zeroth-order post-training possible. This phenomenon has been noted by a number of works in the past 3 years, but most notably in my opinion by Neural Thickets [Yulu Gan and Philip Isola, 2026] and Finetuning with Only Forward Passes [Malladi et al. 2024].
My work is currently supported by kind grants from a number of institutions. I am based out of nowhere.