Moritz Willig
YOU?
Author Swipe
View article: Fodor and Pylyshyn's Legacy -- Still No Human-like Systematic Compositionality in Neural Networks
Fodor and Pylyshyn's Legacy -- Still No Human-like Systematic Compositionality in Neural Networks Open
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 presenting models for robust adaptation to novel environments,…
View article: CausalMan: A physics-based simulator for large-scale causality
CausalMan: A physics-based simulator for large-scale causality Open
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 data generating processes complicates fair benchmarking. In th…
View article: Systems with Switching Causal Relations: A Meta-Causal Perspective
Systems with Switching Causal Relations: A Meta-Causal Perspective Open
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 points in the environmental process can change the qualitative…
View article: $χ$SPN: Characteristic Interventional Sum-Product Networks for Causal Inference in Hybrid Domains
$χ$SPN: Characteristic Interventional Sum-Product Networks for Causal Inference in Hybrid Domains Open
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 propose Characteristic Interventional Sum-Product Network ($χ$S…
View article: “Do Not Disturb My Circles!” Identifying the Type of Counterfactual at Hand (Short Paper)
“Do Not Disturb My Circles!” Identifying the Type of Counterfactual at Hand (Short Paper) Open
When the phenomena of interest are in need of explanation, we are often in search of the underlying root causes. Causal inference provides tools for identifying these root causes—by performing interventions on suitably chosen variables we …
View article: Do Not Marginalize Mechanisms, Rather Consolidate!
Do Not Marginalize Mechanisms, Rather Consolidate! Open
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 number of variables and complexity of interactions between the…
View article: Causal Parrots: Large Language Models May Talk Causality But Are Not Causal
Causal Parrots: Large Language Models May Talk Causality But Are Not Causal Open
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 sometimes we might feel otherwise. To this end, we define and e…
View article: Pearl Causal Hierarchy on Image Data: Intricacies & Challenges
Pearl Causal Hierarchy on Image Data: Intricacies & Challenges Open
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 any other growing subfield, patience seems to be a virtue si…
View article: Continual Causal Abstractions
Continual Causal Abstractions Open
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 to a different level of detail that is both consistent with …
View article: Can Foundation Models Talk Causality?
Can Foundation Models Talk Causality? Open
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 arguably impressive results as evidence to the scaling hypothesis,…
View article: The Causal Loss: Driving Correlation to Imply Causation
The Causal Loss: Driving Correlation to Imply Causation Open
Most algorithms in classical and contemporary machine learning focus on correlation-based dependence between features to drive performance. Although success has been observed in many relevant problems, these algorithms fail when the underl…
View article: Learning to Play the Chess Variant Crazyhouse Above World Champion Level With Deep Neural Networks and Human Data
Learning to Play the Chess Variant Crazyhouse Above World Champion Level With Deep Neural Networks and Human Data Open
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 starting from zero knowledge has been shown to yield impressive …