Publications

Conference and Journal Papers

APM: Evaluating Style Personalization in LLMs with Arbitrary Preference Mappings
Philipp Spohn, Leander Girrbach and Zeynep Akata
NeurIPS 2026 (Evaluations & Benchmarks Track)
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

Workshop Papers

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
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
Automatic Concept Extraction for Learning Domain Modeling: A Weakly Supervised Approach Using Contextualized Word Embeddings
Kordula De Kuthy, Leander Girrbach, and Detmar Meurers
ACL BEA Workshop 2025
Paper
Straight-Through Gradient Estimation for Hard Attention
Leander Girrbach
ACL SIGMORPHON 2023
Paper

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
Word Segmentation and Morphological Parsing for Sanskrit
Jingwen Li and Leander Girrbach
arXiv 2022
Paper