Phillip Lippe

Phillip Lippe

PhD student in Artificial Intelligence

University of Amsterdam, QUVA

Biography

I’m a PhD student in the QUVA lab at the University of Amsterdam supervised by Efstratios Gavves and Taco Cohen. I am also part of the ELLIS PhD program in cooperation with Qualcomm. My research focuses on the intersection of causality and machine learning, particularly on temporal data. Additionally, I am interested in generative modeling, especially of discrete structure such as graphs, reinforcement learning, and natural language processing.

Before starting the PhD, I completed my Master degree in Artificial Intelligence at the University of Amsterdam, with my Master thesis on Categorical Normalizing Flows. My Bachelor was a cooperative study program between the DHBW Stuttgart and Daimler/Mercedes-Benz, where I conducted three research internships on deep learning and computer vision for autonomous driving.

Interests
  • Causality and Deep Learning
  • Generative models
  • Discrete structure learning
Education
  • MSc Artificial Intelligence, 2020

    University of Amsterdam

  • BSc Computer Science, 2018

    DHBW Stuttgart

News

  • I have been accepted to the OxML 2021 summer school. Looking forward to meeting a lot of new people!
  • Our work on “Categorical Normalizing Flows via Continuous Transformations” has been accepted to ICLR 2021.
  • We have reached 4th place in the NeurIPS 2020 challenge “Hateful Meme Detection”, hosted by Facebook AI. We summarized our approach in this paper, and presented it at NeurIPS 2020.
  • For the Deep Learning course 2020 at UvA, I created a series of Jupyter notebooks to teach important concepts from an implementation perspective. The notebooks can be found here