Search

  • Home
  • Publications
  • People
  • Join Us
Patrik Reizinger

Patrik Reizinger

PhD candidate

MPI for Intelligent Systems

University of Tübingen

IMPRS-IS

ELLIS

Interests
  • Identifiable Representation Learning
  • Causal Representation Learning
  • Self-Supervised Learning
  • Out-of-Distribution Generalization
Education
  • Ph.D. in Machine Learning, current

    University of Tuebingen

  • M.Sc. in Electrical Engineering, 2021

    Budapest Univeristy of Technology and Economics

  • B.Sc. in Electrical Engineering, 2019

    Budapest Univeristy of Technology and Economics

Latest

  • Cross-Entropy Is All You Need To Invert the Data Generating Process
  • Rule Extrapolation in Language Models: A Study of Compositional Generalization on OOD Prompts
  • InfoNCE: Identifying the Gap Between Theory and Practice
  • Identifiable Exchangeable Mechanisms for Causal Structure and Representation Learning
  • Position: Understanding LLMs requires more than statistical generalization
  • Understanding LLMs Requires More Than Statistical Generalization
  • An interventional perspective on identifiability in gaussian lti systems with independent component analysis
  • Jacobian-based Causal Discovery with Nonlinear ICA
  • Embrace the Gap: VAEs Perform Independent Mechanism Analysis
  • Content suppresses style: dimensionality collapse in contrastive learning

© 2025 AG Brendel

Published with Wowchemy — the free, open source website builder that empowers creators.

Cite
Copy Download