27 citations · 48 across the 14 of their papers we have counts for
14 papers
xWhyL: Causal Interactive Learning
Nicholas Tagliapietra, Florian Peter Busch, Moritz Willig +4
Explanations are central to causal reasoning, and cognitive science has long established that the human drive to explain is itself a mechanism for learning about causality. Despite…
CausalSteward: An Agentic Divide-Conquer-Combine Copilot for Causal Discovery
Nicholas Tagliapietra, Gian Lorenzo Marchioni, Moritz Willig +3
Learning causal models from high-dimensional data is a significant challenge, particularly in real-world settings where violations of core assumptions lead to causal identifiabilit…
Tags for DAGs: Graph Refinement with Meta-Informed Relations
Florian Peter Busch, Moritz Willig, Florian Guldan +2
Causal discovery has shifted from data-centric methods to hybrid strategies that integrate semantic knowledge from experts or large language models (LLMs). Such external informatio…
Fodor and Pylyshyn's Legacy: Still No Human-like Systematic Compositionality in Neural Networks
Tim Woydt, Moritz Willig, Antonia Wüst +4
Strong meta-learning capabilities for systematic compositionality are emerging as an important skill for navigating the complex and changing tasks of today's world. However, in pre…
CausalMan: A physics-based simulator for large-scale causality
Nicholas Tagliapietra, Juergen Luettin, Lavdim Halilaj +3
A comprehensive understanding of causality is critical for navigating and operating within today's complex real-world systems. The absence of realistic causal models with known dat…
Systems with Switching Causal Relations: A Meta-Causal Perspective
Moritz Willig, Tim Nelson Tobiasch, Florian Peter Busch +3
Most work on causality in machine learning assumes that causal relationships are driven by a constant underlying process. However, the flexibility of agents' actions or tipping poi…
SPN: Characteristic Interventional Sum-Product Networks for Causal Inference in Hybrid Domains
Harsh Poonia, Moritz Willig, Zhongjie Yu +3
Causal inference in hybrid domains, characterized by a mixture of discrete and continuous variables, presents a formidable challenge. We take a step towards this direction and prop…
Do Not Marginalize Mechanisms, Rather Consolidate!
Moritz Willig, Matej Zečević, Devendra Singh Dhami +1
Structural causal models (SCMs) are a powerful tool for understanding the complex causal relationships that underlie many real-world systems. As these systems grow in size, the num…
Causal Parrots: Large Language Models May Talk Causality But Are Not Causal
Matej Zečević, Moritz Willig, Devendra Singh Dhami +1
Some argue scale is all what is needed to achieve AI, covering even causal models. We make it clear that large language models (LLMs) cannot be causal and give reason onto why some…
Continual Causal Abstractions
Matej Zečević, Moritz Willig, Jonas Seng +1
This short paper discusses continually updated causal abstractions as a potential direction of future research. The key idea is to revise the existing level of causal abstraction t…
Pearl Causal Hierarchy on Image Data: Intricacies & Challenges
Matej Zečević, Moritz Willig, Devendra Singh Dhami +1
Many researchers have voiced their support towards Pearl's counterfactual theory of causation as a stepping stone for AI/ML research's ultimate goal of intelligent systems. As in a…
Can Foundation Models Talk Causality?
Moritz Willig, Matej Zečević, Devendra Singh Dhami +1
Foundation models are subject to an ongoing heated debate, leaving open the question of progress towards AGI and dividing the community into two camps: the ones who see the arguabl…
The Causal Loss: Driving Correlation to Imply Causation
Moritz Willig, Matej Zečević, Devendra Singh Dhami +1
Most algorithms in classical and contemporary machine learning focus on correlation-based dependence between features to drive performance. Although success has been observed in ma…
Learning to play the Chess Variant Crazyhouse above World Champion Level with Deep Neural Networks and Human Data
Johannes Czech, Moritz Willig, Alena Beyer +2
Deep neural networks have been successfully applied in learning the board games Go, chess and shogi without prior knowledge by making use of reinforcement learning. Although starti…