Email: elohn [at] cs [dot] cmu [dot] edu

Hello, my name is Evan lohn. I am a PhD student (began Fall 2021) in the Computer Science Department at Carnegie Mellon University. I was advised by Marijn Heule and Jeremy Avigad for my first two years, and I will be leaving with a Masters degree Summer 2024.

In the past, I worked with Pieter Abbeel at the BAIR lab on applications of deep unsupervised learning to image compression. I'm still very much interested in potential applications of deep unsupervised learning (especially for theorem proving), but more recently I've been approaching theorem proving from the perspective of automated reasoning and interactive theorem provers like Lean. I'm broadly interested in automated and interactive theorem proving, as well as applications of LLMs to reasoning. Here is a blog post I wrote about my recent work on a benchmark for the theorem proving agents' code reasoning abilities.

- Jonathan Ho, Evan Lohn, and Pieter Abbeel

**Compression with flows via local bits-back coding**(2019) [arxiv]

In*NeurIPS 2019* - Evan Lohn, Chris Lambert, and Marijn Heule

**Compact Symmetry Breaking for Tournaments**(2022) [paper] [code]

In*FMCAD 2022*