Folgen
Florian E. Dorner
Florian E. Dorner
ETH Zürich, Max-Planck Institut für Intelligente Systeme
Bestätigte E-Mail-Adresse bei istp.ethz.ch
Titel
Zitiert von
Zitiert von
Jahr
Forecasting AI progress: A research agenda
R Gruetzemacher, FE Dorner, N Bernaola-Alvarez, C Giattino, D Manheim
Technological Forecasting and Social Change 170, 120909, 2021
352021
Do personality tests generalize to Large Language Models?
FE Dorner, T Sühr, S Samadi, A Kelava
Socially Responsible Language Modelling Research (SoLaR) 2023 Workshop at …, 2023
122023
Measuring Progress in Deep Reinforcement Learning Sample Efficiency
FE Dorner
arXiv preprint arXiv:2102.04881, 2021
102021
Algorithmic collusion: A critical review
FE Dorner
arXiv preprint arXiv:2110.04740, 2021
92021
Human-Guided Fair Classification for Natural Language Processing
FE Dorner, M Peychev, N Konstantinov, N Goel, E Ash, M Vechev
ICLR 2023, 2022
52022
Incentivizing Honesty among Competitors in Collaborative Learning and Optimization
FE Dorner, N Konstantinov, G Pashaliev, M Vechev
NeurIPS 2023, 2023
42023
Training on the Test Task Confounds Evaluation and Emergence
R Dominguez-Olmedo, FE Dorner, M Hardt
arXiv preprint arXiv:2407.07890, 2024
2024
Whose Preferences? Differences in Fairness Preferences and Their Impact on the Fairness of AI Utilizing Human Feedback
E Agis Lerner, FE Dorner, E Ash, N Goel
ACL 2024, 2024
2024
Don't Label Twice: Quantity Beats Quality when Comparing Binary Classifiers on a Budget
FE Dorner, M Hardt
ICML 2024, 2024
2024
Das System kann den Vorgang jetzt nicht ausführen. Versuchen Sie es später erneut.
Artikel 1–9