Some ongoing and past projects.
This paper covers how to construct diffusion processes on data manifolds. See the full blog post here.
On the theoretical side, am currently exploring Stochastic Analysis on Manifolds and its implications for sampling. On a more applied side, I am working on geometric aspects and phase transitions in (mostly image data) score-based reverse diffusion models.
I also have a very infrequent YouTube channel, where i talk about whatever i feel like. I've made a few albums e.g. here, some of which you can find on my Spotify.