Differences
This shows you the differences between two versions of the page.
Next revision | Previous revision | ||
members:tomani [2019/07/18 15:23] Quirin Lohr created |
members:tomani [2024/04/18 19:28] (current) Christian Tomani |
||
---|---|---|---|
Line 1: | Line 1: | ||
< | < | ||
+ | |||
+ | ==== Brief Bio ==== | ||
+ | Find me on [[https:// | ||
+ | |||
+ | I am a PhD student at the Technical University of Munich at the Chair of [[: | ||
+ | |||
+ | |||
+ | <fs large> | ||
+ | |||
+ | **Meta** (New York)\\ | ||
+ | //Paper:// Uncertainty-Based Abstention in LLMs Improves Safety and Reduces Hallucinations (C Tomani, Kamalika C, Ivan E, Daniel C, Mark I), In arXiv preprint, 2024. | ||
+ | |||
+ | **Google** (San Francisco Bay Area)\\ | ||
+ | //Paper:// Quality Control at Your Fingertips: Quality-Aware Translation Models (C Tomani, D Vilar and M Freitag and C Cherry and S Naskar and M Finkelstein and D Cremers), In arXiv preprint, 2023. | ||
+ | |||
+ | **Siemens** (Munich)\\ | ||
+ | //Paper:// Towards Trustworthy Predictions from Deep Neural Networks with Fast Adversarial Calibration (C Tomani and F Buettner), AAAI, 2021. | ||
+ | |||
+ | |||
+ | <fs large> | ||
+ | |||
+ | **University of Oxford**\\ | ||
+ | Machine Learning Group - Department of Engineering Science | ||
+ | |||
+ | **University of California Berkeley**\\ | ||
+ | Artificial Intelligence Research Lab (BAIR) - Redwood Center for Theoretical Neuroscience | ||
+ | |||
+ | |||
+ | |||
+ | |||
+ | ==== My Work ==== | ||
+ | I am interested in developing reliable, robust, and reasoning-based large language models (LLMs) and multimodal models. Moreover, I am fascinated by enhancing the reasoning ability, safety and uncertainty awareness of generative models through pre-training and post-training (via fine-tuning and alignment to human preferences) to develop grounded world models and improve factuality and trustworthiness. | ||
+ | |||
+ | My work covers a large spectrum of Machine Learning and Deep Learning topics. Projects of mine include reliable, reasoning-based, | ||
+ | |||
+ | |||
+ | ==== Publications ==== | ||
+ | * **Beyond In-Domain Scenarios: Robust Density-Aware Calibration**, | ||
+ | < | ||
+ | </ | ||
+ | < | ||
+ | |||
+ | |||
+ | * **Parameterized Temperature Scaling for Boosting the Expressive Power in Post-Hoc Uncertainty Calibration**, | ||
+ | < | ||
+ | </ | ||
+ | < | ||
+ | |||
+ | |||
+ | * **Post-hoc Uncertainty Calibration for Domain Drift Scenarios**, | ||
+ | < | ||
+ | </ | ||
+ | < | ||
+ | |||
+ | |||
+ | < | ||
+ | < | ||
+ | < | ||
+ | </ | ||
+ |