Hi! I am Thomas (Hanwen) Zhu. I am currently a first-year MS in Machine Learning student at CMU, working on applying language models to solving mathematical problems at the L3 Lab with Prof. Sean Welleck. My research interests more broadly include advancing reasoning abilities in machine learning models in a robust and scalable way.

I received BA Mathematics and Computer Science from Oxford, where I graduated top first. I had the priviledge to work with Ruining Li and Tomas Jakab at VGG in applying diffusion models to 3D generation of human-object interactions. I also worked with a team at OxAI in developing a benchmark for gender bias in large vision-language models.

I am always excited to hear about potential collaborations or ideas. Please contact me at [email protected].

Publications

DreamHOI: Subject-Driven Generation of 3D Human-Object Interactions with Diffusion Priors
Thomas Zhu, Ruining Li*, Tomas Jakab*
Website Paper GitHub
In preprint

miniCTX: Neural Theorem Proving with (Long-)Contexts
Jiewen Hu, Thomas Zhu, Sean Welleck
Paper Dataset
AITP 2024

VisoGender: A dataset for benchmarking gender bias in image-text pronoun resolution
Siobhan Mackenzie Hall, Fernanda Gonçalves Abrantes, Thomas Hanwen Zhu, Grace Sodunke, Aleksandar Shtedritski, Hannah Rose Kirk
Paper GitHub
NeurIPS Datasets and Benchmarks 2023