Profile

Leander Girrbach is a Ph.D. candidate under the supervision of Prof. Zeynep Akata. He received his bachelor's degree in computational linguistics from Heidelberg University in 2021 and his master's degree also in computational linguistics from the University of Tübingen in 2023.

His primary interests center around gaining a better understanding of deep learning models - understanding how neural networks work and constructing models that are more interpretable.

Publications

Conferences and Journals

 

APM: Evaluating Style Personalization in LLMs with Arbitrary Preference Mappings.
Philipp Spohn, Leander Girrbach and Zeynep Akata
NeurIPS 2026
Paper

 

Sparse Autoencoders are Topic Models.
Leander Girrbach and Zeynep Akata
ICML 2026
Paper | Code

 

Person-Centric Annotations of LAION-400M: Auditing Bias and Its Transfer to Models.
Leander Girrbach, Stephan Alaniz, Genevieve Smith, Trevor Darrell and Zeynep Akata
ICLR 2026
Paper | Code

 

Are Reasoning LLMs Robust to Interventions on Their Chain-of-Thought?
Alexander von Recum, Leander Girrbach, and Zeynep Akata
ICLR 2026
Paper | Code

 

A Systematic Study of In-the-Wild Model Merging for Large Language Models.
Oguz Kagan Hitit, Leander Girrbach, and Zeynep Akata
TMLR (03/2026)
Paper | Code

 

SUB: Benchmarking CBM Generalization via Synthetic Attribute Substitutions.
Jessica Bader, Leander Girrbach, Stephan Alaniz and Zeynep Akata
ICCV 2025
Paper | Code

 

Revealing and Reducing Gender Biases in Vision and Language Assistants (VLAs).
Leander Girrbach, Stephan Alaniz, Yiran Huang, Trevor Darrell and Zeynep Akata
ICLR 2025
Paper | Code

 

Decoupling Angles and Strength in Low-rank Adaptation.
Massimo Bini, Leander Girrbach and Zeynep Akata
ICLR 2025
Paper | Code

 

Addressing caveats of neural persistence with deep graph persistence.
Leander Girrbach, Anders Christensen, Ole Winther, Zeynep Akata and A. Sophia Koepke
TMLR (11/2023)
Paper | Code

Workshops

 

Align-then-Unlearn: Embedding Alignment for LLM Unlearning.
Philipp Spohn, Leander Girrbach, Jessica Bader and Zeynep Akata
ICML 2025 Workshop on Machine Unlearning for Generative AI
Paper | Code

 

A Latent-Timescale Perspective on Continual Learning in Language Models.
Philipp Spohn, Leander Girrbach and Zeynep Akata
NeurIPS 2026 Workshop on Foundations of LLM Post-Training in Changing Environments

Preprints

 

Agents Are Systems, Not Models: Rethinking Agentic Evaluation.
Luis Wiedmann, Leander Girrbach, Cordelia Schmid and Zeynep Akata
arXiv 2026
Paper

 

A large scale analysis of gender biases in text-to-image generative models.
Leander Girrbach, Stephan Alaniz, Genevieve Smith and Zeynep Akata
arXiv 2025
Paper