Cameron Braunstein

About

My name is Cameron Braunstein, and I am a PhD student in Computer Science at Saarland University in Saarbrücken, Germany. I am supervised by Eddy Ilg and Mariya Toneva, as a member of the first cohort of the Research Training Group Neuroexplicit Models of Language, Vision, and Action. My goal is to develop explainable vision-language AI models which are well aligned with human cognition.

Prior to my PhD, I received my Master's degree in Data Science and Artificial Intelligence from Saarland University in 2023. The research from my Master's thesis, Quantum-Hybrid Stereo Matching With Nonlinear Regularization and Spatial Pyramids, was published at the International Conference on 3D Vision 2024. I received my Bachelor's degree in Computer Science and Mathematics from Brandeis University in Waltham, Massachusetts in 2019.

I am passionate about tutoring and contributing to my academic community. I have been a teaching assistant for numerous courses. In addition to my Master's thesis, I delivered a talk on Quantum Computing at the Max Planck Institute for Informatics. I am currently serving as a PhD student representative for my Research Training Group.

In my spare time, I enjoy classical piano, chess, and studying mathematics. You can find my full CV here.

Research Works

SLayR: Scene Layout Generation with Rectified Flow

Cameron Braunstein, Hevra Petekkaya, Jan Eric Lenssen, Mariya Toneva, Eddy Ilg

Transactions on Machine Learning Research (TMLR), 2026 · arXiv

The One Where They Brain-Tune for Social Cognition: Multi-Modal Brain-Tuning on Friends

Nico Policzer, Cameron Braunstein, Mariya Toneva

NeurIPS 2025 Workshop on Interpreting Cognition in Deep Learning Models · arXiv

3DFroMLLM: 3D Prototype Generation only from Pretrained Multimodal LLMs

Noor Ahmed, Cameron Braunstein, Steffen Eger, Eddy Ilg

Preprint, 2025 · arXiv

Quantum-Hybrid Stereo Matching With Nonlinear Regularization and Spatial Pyramids

Cameron Braunstein, Eddy Ilg, Vladislav Golyanik

International Conference on 3D Vision (3DV), 2024 · arXiv

Open Source Projects

Cluster Watcher

A dependency-free Python tool for checking multiple Slurm clusters over SSH, with terminal, browser, and VS Code interfaces for capacity, jobs, wait estimates, logs, and safe job controls.

View on GitHub

file_golem

A file I/O utility for managing complex projects with multiple datasets, project locations, naming conventions, and third-party codebases.

View on PyPI

ml_golem

A configurable toolkit for simplifying machine-learning training and inference pipelines, built on file_golem for consistent project organization.

View on PyPI