Michael Neumayr

M.Sc. Computer Science @ TUM

prof_pic.png

I am a final-year Master’s student interested in 3D computer vision and generative models. Currently, I am doing my thesis at University of Toronto under the supervision of David Lindell and Sherwin Bahmani, co-supervised by Matthias Nießner at TUM.

Previously, I worked as research assistant at the Ommerlab with Stephan Baumann. During my studies, I worked on several projects, including a course project on generalizable novel view synthesis supervised by David Rozenberszki and a research project on diffusion models in medical imaging under Cosmin Bercea and Julia Schnabel.

I am engaged in the educational offerings of TUM.ai for over two years and organize the TUM.ai paper reading circle on (3D) computer vision and generative modeling. I obtained my B.Sc. in Computer Science and B.A. in Philosophy from the University of Munich.

Publications

  1. attribute.png
    Continuous, Subject-Specific Attribute Control in T2I Models by Identifying Semantic Directions
    Stefan Andreas Baumann, Felix Krause , Michael Neumayr, and 4 more authors
    2025
    arXiv PDF Code Website
    6 Google Scholar citations
  2. autoddpm.gif
    Mask, Stitch, and Re-Sample: Enhancing Robustness and Generalizability in Anomaly Detection through Automatic Diffusion Models
    Cosmin I Bercea*, Michael Neumayr*, Daniel Rueckert, and 1 more author
    In ICML 3rd Workshop on Interpretable Machine Learning in Healthcare (IMLH) , 2023
    arXiv HTML PDF Code Website
    35 Google Scholar citations
  3. dipencoder.png
    The Dipencoder: Enforcing multimodality in autoencoders
    Collin Leiber, Lena GM Bauer , Michael Neumayr, and 2 more authors
    In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining , 2022
    HTML PDF Code Slides
    9 Google Scholar citations

News

Sep 01, 2024 I joined the lab of David Lindell at the University of Toronto as visiting graduate student for seven months to do my master thesis.
Oct 02, 2023 I attended ICCV 2023 in Paris from October 2, 2023 - October 6, 2023.
Jun 20, 2023 Our paper Mask, Stitch, and Re-Sample: Enhancing Robustness and Generalizability in Anomaly Detection through Automatic Diffusion Models got accepted to IMLH 2023 (ICML Workshop in third iteration).
Oct 01, 2022 I started my Master of Science in Computer Science at the Technical University of Munich (TUM).
Sep 30, 2022 I finished my Bachelor of Arts in Philosophy at the University of Munich (LMU).
Aug 14, 2022 I attended KDD 2022 in Washington from August 14, 2022 - August 18, 2022.
May 19, 2022 Our paper The DipEncoder: Enforcing Multimodality in Autoencoders based on the findings from my Bachelor’s thesis got accepted to KDD 2022.
Feb 12, 2022 I finished my Bachelor of Science in Computer Science at the University of Munich (LMU).