Mario Fritz
- Papers
- 8
Cite
Notes
Only stored in your browser.
Authored papers
8MaxSup: Overcoming Representation Collapse in Label Smoothing
arXiv 2025
Balancing Diversity and Risk in LLM Sampling: How to Select Your Method and Parameter for Open-Ended Text Generation
arXiv 2024
LLM Task Interference: An Initial Study on the Impact of Task-Switch in Conversational History
arXiv 2024
Adaptive Hierarchical Certification for Segmentation using Randomized Smoothing
arXiv 2024
FullCert: Deterministic End-to-End Certification for Training and Inference of Neural Networks
arXiv 2024
Dataset and Lessons Learned from the 2024 SaTML LLM Capture-the-Flag Competition
arXiv 2024
Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection
arXiv 2023
B-cos Networks: Alignment is All We Need for Interpretability
CVPR 2022 1
Affiliations
Frequent co-authors
10from 8 papers