Takip et
Roman Lutz
Roman Lutz
Responsible AI Engineer at Microsoft
microsoft.com üzerinde doğrulanmış e-posta adresine sahip - Ana Sayfa
Başlık
Alıntı yapanlar
Alıntı yapanlar
Yıl
Fairlearn: A toolkit for assessing and improving fairness in AI
S Bird, M Dudik, R Edgar, B Horn, R Lutz, V Milan, M Sameki, H Wallach, ...
https://www.microsoft.com/en-us/research/publication/fairlearn-a-toolkit-for …, 2020
4812020
Fairlearn: Assessing and improving fairness of AI systems
H Weerts, M Dudík, R Edgar, A Jalali, R Lutz, M Madaio
Journal of Machine Learning Research 24 (257), 1-8, 2023
852023
Adaptive Large Neighborhood Search
R Lutz
University of Ulm OPARU http://dx.doi.org/10.18725/OPARU-3237, 2015
302015
Fantasy Football Prediction
R Lutz
arXiv preprint arXiv:1505.06918, 2015
182015
A Framework for Automated Measurement of Responsible AI Harms in Generative AI Applications
A Magooda, A Helyar, K Jackson, D Sullivan, C Atalla, E Sheng, D Vann, ...
arXiv preprint arXiv:2310.17750, 2023
102023
Security and Privacy in Future Internet Architectures-Benefits and Challenges of Content Centric Networks
R Lutz
arXiv preprint arXiv:1601.01278, 2016
102016
Phi-3 safety post-training: Aligning language models with a" break-fix" cycle
E Haider, D Perez-Becker, T Portet, P Madan, A Garg, A Ashfaq, ...
arXiv preprint arXiv:2407.13833, 2024
52024
NFL Play Prediction
B Teich, R Lutz, V Kassarnig
arXiv preprint arXiv:1601.00574 [cs.LG], 2016
42016
PyRIT: A Framework for Security Risk Identification and Red Teaming in Generative AI System
GDL Munoz, AJ Minnich, R Lutz, R Lundeen, RSR Dheekonda, ...
arXiv preprint arXiv:2410.02828, 2024
1*2024
Lessons From Red Teaming 100 Generative AI Products
B Bullwinkel, A Minnich, S Chawla, G Lopez, M Pouliot, W Maxwell, ...
arXiv preprint arXiv:2501.07238, 2025
2025
Sistem, işlemi şu anda gerçekleştiremiyor. Daha sonra yeniden deneyin.
Makaleler 1–10