Posts

Energy-Tweedie: Score meets Score, Energy meets Energy has been accepted to NeurIPS 2026.

We have a new preprint out on benchmarking agentic causal data-science.

Approaching an unknown communication system has been accepted to Royal Society Open Science.

A 60-minute fireside chat on Distributional Autoencoders Know the Score, hosted by Ploutos.

A short announcement of the Energy-Tweedie preprint and its publication page.

A talk at the Simons Institute on using deep generative models to study sperm whale communication.

We have a pre-print out based on our work with Project CETI, an initiative to decipher sperm whale communication using machine learning. In the paper, we combine approaches that help discover how known properties of human language are learned by generative models when trained on labeled speech audio data with methodology inspired by causal inference and apply it to the communication system of sperm whales, for which we do not have any such ground truth.

A brief introduction to diffusion models

Given that the semester’s over, I have finally gotten around to updating the site. We have a pre-print out based on the work I did during my internship last summer. It examines the problem of inferring the characteristics of different people involved in the process of translating and reviewing text by using Hierarchical Bayesian Models.

NOTE: This is a migration of an old post from my previous blog. In this post I’d like to briefly sketch my personal setup for git repositories, focusing on their backup.