Alexandru Țifrea

I am a Research Scientist at Google DeepMind currently working on developing better algorithms for large language model post-training. Prior to that, I obtained my PhD from the Department of Computer Science of ETH Zürich, working under the supervision of Fanny Yang in the Statistical Machine Learning group. Before that I completed a MSc degree in Computer Science at ETH Zürich and a BSc degree in Computer Engineering at Politehnica University Bucharest.
I’m broadly interested in various theoretical and methodological aspects of trustworthy ML (distribution shifts, fairness, uncertainty estimation), data-efficient learning (active learning, semi-supervised learning) and representation learning.
news
Feb 15, 2025 | Together with Amartya Sanyal, will organize a tutorial at AAAI 2025 titled Building trustworthy ML: The role of label quality and availability (slides). |
Jan 22, 2025 | Our paper on multi-objective learning in high dimensions has been accepted at AISTATS 2025. |
Nov 15, 2024 | Excited to join Google DeepMind to work on large language model post-training. |
Jul 15, 2024 | I have defended my PhD thesis titled Towards Trustworthy Machine Learning Using Unlabeled Data 🎉🎉🎉 |
May 7, 2024 | Our paper introducing FRAPPÉ, a general framework for training a post-processing group fairness mitigation has been accepted at ICML2024. |