Chris Gumbsch

Hi, I'm Christian Gumbsch. I'm a postdoc at the University of Amsterdam working with Stratis Gavves. Previously, I did my PhD at the Max Planck Institute for Intelligent Systems and University of Tübingen jointly supervised by Georg Martius and Martin Butz, followed by a postdoc at the TU Dresden working with Katharina von Kriegstein.


Research interest

I am fascinated by the question of how humans and other animals learn adaptive goal-directed behavior from their experience. My research goal is to help the development of autonomous embodied agents with a similar skillset. To work towards this goal, I follow two research directions:


1. AI research: I research how to improve decision-making in deep learning agents. More specifically, I work towards agents that explore interesting behavior, plan far into the future, and can reuse their knowledge in new situations. This includes research on generalization, temporal abstraction, world models, and intrinsic motivation.


2. Cognitive modeling: I use the same methods to build computational cognitive models. Here I hope to shine light into the mechanisms and representations that give rise to the adaptive behavior of humans. This includes modeling event segmentation, epistemic gaze behavior, and multimodal speech processing.


Chris Gumbsch Chris Gumbsch

Showing selected papers. Toggle to view the full list. See Google Scholar for recent publications.

Causal Process Models - Reframing Dynamic Causal Graph Discovery as a Reinforcement Learning Problem

Turan Orujlu, Christian Gumbsch, Martin V. Butz & Charley M. Wu
CLeaR 2026
Paper

SENSEI - Semantic Exploration Guided by Foundation Models For Learning Versatile World Models

Cansu Sancaktar*, Christian Gumbsch*, Andrii Zadaianchuk, Pavel Kolev & Georg Martius
ICML 2025 (27%), *equal contribution
Paper, Website, Video

Contextualizing Predictive Minds

Martin V. Butz, Maximilian Mittenbühler, Sarah Schwöbel, Asya Achimova, Christian Gumbsch, Sebastian Otte & Stefan Kiebel
Neuroscience & Biobehavioral Reviews, 2025
Paper

Infants infer and predict coherent event interactions - Modeling cognitive development

Johanna K. Theuer, Nadine N. Koch, Christian Gumbsch , Birgit Elsner & Martin V. Butz
PLoS One, 2024
Paper

Learning Hierarchical World Models with Adaptive Temporal Abstractions from Discrete Latent Dynamics

Christian Gumbsch, Noor Sajid, Georg Martius & Martin V. Butz
ICLR 2024 (spotlight, 5%)
Paper, Code, Twitter, Website

Developing Hierarchical Anticipations from Event Segmentation

Christian Gumbsch, Maurits Adam, Birgit Elsner, Georg Martius & Martin V. Butz
IEEE ICDL, 2022 ( SmartBot challenge winner , oral)
Paper, Code, Twitter

Inference of affordances and active motor control in simulated agents

Fedor Scholz, Christian Gumbsch, Sebastian Otte & Martin V. Butz
Frontiers in Neurorobotics, 2022
Paper

Intelligent Problem-Solving as Integrated Hierarchical Reinforcement Learning

Manfred Eppe, Christian Gumbsch, Matthias Kerzel, Phuong D. H. Nguyen, Martin V. Butz & Stefan Wermter
Nature Machine Intelligence, 2022
Paper

GateL0RD - Sparsely Changing Latent States for Prediction and Planning in POMDPs

Christian Gumbsch, Martin V. Butz & Georg Martius
NeurIPS 2021 (26%)
Paper, Code, Twitter

Goal‐Anticipatory Gaze in Infants from Event‐Predictive Learning and Inference

Christian Gumbsch, Maurits Adam, Birgit Elsner & Martin V. Butz
Cognitive Science, 2021
Paper, Code

The Impact of Action Effects on Infants’ Predictive Gaze Shifts for a Non-Human Grasping Action

Maurits Adam, Christian Gumbsch, Martin V. Butz & Birgit Elsner
Frontiers in Psychology, 2021
Paper

Segmenting Behavioral Primitives from Sensorimotor Exploration for Event-Based Planning

Christian Gumbsch, Martin V. Butz* & Georg Martius*
IEEE TCDS, 2019
Paper, Video