University of Luxembourg

AI & ML interests

None defined yet.

Recent Activity

mgubri  authored a paper about 2 months ago

Privacy Collapse: Benign Fine-Tuning Can Break Contextual Privacy in Language Models

mgubri  submitted a paper about 2 months ago

Privacy Collapse: Benign Fine-Tuning Can Break Contextual Privacy in Language Models

mgubri  authored a paper 5 months ago

Is Multilingual LLM Watermarking Truly Multilingual? A Simple Back-Translation Solution

View all activity

Team members 108