Publications
News
Events
Intranet
About
Who we are
German AI Centers
Diversity & Inclusion
Governance & Boards
Statistics
Contact
People
Directors
Management
Research Groups
Junior Research Groups
Thomas Bayes Fellows
Junior Members
Former Members
Research
A | Foundations of ML
B | Perception, Vision and NLP
C | Domain-specific ML
Featured Projects
Academic Partnerships
Research Blog
Top Tier Work
Awards, Grants & Prizes
Opportunities
For Junior Members
For PhD Applicants
For School Graduates
Job Opportunities
Transfer
Industry Partnerships
Entrepreneurship
ML Consulting Services
Schools & Outreach
Continuing Education
Publications
News
Events
Intranet
Home
|
Tags
| #p-kasneci-gjergji
#p-kasneci-gjergji
ZPK+26
Reinforcement Unlearning via Group Relative Policy Optimization
ICLR 2026
#p-kasneci-gjergji
YMZ+26
Moral Lenses, Political Coordinates: Towards Ideological Positioning of Morally Conditioned LLMs
Preprint (Jan. 2026)
#p-kasneci-gjergji
#p-kreuter
Back to Top
0001-01-01 - Last modified: 0001-01-01