Stephan Alaniz
Postdoctoral Researcher



  • Ph.D. candidate, Max Planck Institute for Informatics and University of Tübingen (previously at University of Amsterdam), 2017 - present
  • M.Sc. Computer Science, TU Berlin, 2014 - 2017
  • B.Sc. Applied Computer Science, DHBW Mannheim, 2011 - 2014


  • "Abstracting Sketches through Simple Primitives", Stephan Alaniz, Massimiliano Mancini, Anjan Dutta, Diego Marcos, Zeynep Akata, European Conference on Computer Vision, ECCV 2022
  • "Compositional Mixture Representations for Vision and Text", Stephan Alaniz, Marco Federici, Zeynep Akata, Workshop on Learning with Limited Labelled Data for Image and Video Understanding (L3D-IVU), CVPR 2022
  • "Semantic Image Synthesis with Semantically Coupled VQ-Model", Stephan Alaniz *, Thomas Hummel *, Zeynep Akata, Workshop on Deep Generative Models for Highly Structured Data (DGM4HSD), ICLR 2022
  • "Learning Decision Trees Recurrently Through Communication", Stephan Alaniz, Diego Marcos, Bernt Schiele, Zeynep Akata, IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2021
  • "Modeling Conceptual Understanding in Image Reference Games", Rodolfo Corona, Stephan Alaniz, Zeynep Akata, Neural Information Processing Systems, NeurIPS 2019
  • "XOC: Explainable Observer-Classifier for Explainable Binary Decisions", Stephan Alaniz, Zeynep Akata ArXiv preprint 2019
  • "Deep Reinforcement Learning with Model Learning and Monte Carlo Tree Search in Minecraft", Stephan Alaniz, Multidisciplinary Conference on Reinforcement Learning and Decision Making (RLDM) 2017


Deep Learning, Explainable AI, Representation Learning, Reinforcement Learning