Moritz Willig
Scholar

Moritz Willig

Google Scholar ID: 1EDRWTsAAAAJ
PhD Candidate, AIML Lab, TU Darmstadt
causal modelinglarge language modelsreasoning
Citations & Impact
All-time
Citations
278
 
H-index
6
 
i10-index
4
 
Publications
20
 
Co-authors
20
list available
Resume (English only)
Academic Achievements
  • Paper 'When Causal Dynamics Matter: Adapting Causal Strategies through Meta-Aware Interventions' accepted at NeurIPS 2025.
  • Paper 'Systems with switching causal relations: A meta-causal perspective' accepted as an ICLR 2025 Spotlight paper.
  • Published 'Causal Parrots: Large Language Models May Talk Causality But Are Not Causal' in TMLR 2023.
  • Published 'Do not marginalize mechanisms, rather consolidate!' at NeurIPS 2023.
  • Multiple 2025 preprints on arXiv covering causal edge direction, systematic compositionality in neural networks, and physics-based causal simulation.
  • Recognized as a top reviewer at NeurIPS 2025 and ICML 2025, and notable reviewer at ICLR 2025.
  • Gave a contributed talk at the Winter School on Causality and Explainable AI, Sorbonne University, October 2025.