Christian Tomani

Publication Activity (10 Years)

Years Active: 2020-2024
Publications (10 Years): 13

Top Topics

Top Venues

Publications

Christian Tomani, Kamalika Chaudhuri, Ivan Evtimov, Daniel Cremers, Mark Ibrahim
Uncertainty-Based Abstention in LLMs Improves Safety and Reduces Hallucinations. CoRR (2024)
Christian Tomani, David Vilar, Markus Freitag, Colin Cherry, Subhajit Naskar, Mara Finkelstein, Daniel Cremers
Quality Control at Your Fingertips: Quality-Aware Translation Models. CoRR (2023)
Christian Tomani, Futa Kai Waseda, Yuesong Shen, Daniel Cremers
Beyond In-Domain Scenarios: Robust Density-Aware Calibration. ICML (2023)
Christian Tomani, Futa Waseda, Yuesong Shen, Daniel Cremers
Beyond In-Domain Scenarios: Robust Density-Aware Calibration. CoRR (2023)
Hans Hao-Hsun Hsu, Yuesong Shen, Christian Tomani, Daniel Cremers
What Makes Graph Neural Networks Miscalibrated? NeurIPS (2022)
Christian Tomani, Daniel Cremers, Florian Buettner
Parameterized Temperature Scaling for Boosting the Expressive Power in Post-Hoc Uncertainty Calibration. ECCV (13) (2022)
Hans Hao-Hsun Hsu, Yuesong Shen, Christian Tomani, Daniel Cremers
What Makes Graph Neural Networks Miscalibrated? CoRR (2022)
Christian Tomani, Daniel Cremers
CHALLENGER: Training with Attribution Maps. CoRR (2022)
Christian Tomani, Daniel Cremers, Florian Buettner
Parameterized Temperature Scaling for Boosting the Expressive Power in Post-Hoc Uncertainty Calibration. CoRR (2021)
Christian Tomani, Sebastian Gruber, Muhammed Ebrar Erdem, Daniel Cremers, Florian Buettner
Post-Hoc Uncertainty Calibration for Domain Drift Scenarios. CVPR (2021)
Christian Tomani, Florian Buettner
Towards Trustworthy Predictions from Deep Neural Networks with Fast Adversarial Calibration. AAAI (2021)
Christian Tomani, Florian Buettner
Towards Trustworthy Predictions from Deep Neural Networks with Fast Adversarial Calibration. CoRR (2020)
Christian Tomani, Sebastian Gruber, Muhammed Ebrar Erdem, Daniel Cremers, Florian Buettner
Post-hoc Uncertainty Calibration for Domain Drift Scenarios. CoRR (2020)