Drift-Resilient TabPFN: In-Context Learning Temporal Distribution Shifts on Tabular Data
NeurIPS 2024 (Main Track); TRL @ NeurIPS 2024; AutoML Conference 2024 (Workshop Track)
Software Engineering · Machine Learning · Quantitative Technology
I am currently a Quantitative Technology Intern at Qube Research & Technologies (QRT) in London. I recently completed an MSc in Computer Science at ETH Zurich, specializing in Machine Intelligence with a Minor in Data Management and graduating with an average grade of 5.61 out of 6.0. My interests include tabular machine learning, time series forecasting, distribution shifts, software engineering, and finance.
Previously, I worked as a Software Engineering Intern on Citadel's Central OTC team, contributing to core production systems in C++ and Python. I also spent seven months at Rheinmetall Air Defence AG, improving the latency, accuracy, and robustness of a real-time computer vision pipeline in C++ and leading its integration with other systems across several departments. As a research assistant at the Machine Learning Lab of the University of Freiburg, I worked on TabPFN, developing missing-value generation and fine-tuning methods that improved benchmark performance.
I earned my BSc in Computer Science from the University of Freiburg with an average grade of 1.1 (top 2%), focusing on machine learning and algorithm development.
NeurIPS 2024 (Main Track); TRL @ NeurIPS 2024; AutoML Conference 2024 (Workshop Track)
MSc Thesis, ETH Zurich, 2026; ETH Research Collection