Hi! I am Merve Gürel
I am an assistant professor in Computer Science at the Delft University of Technology (TU Delft). I am a member of the Pattern Recognition Laboratory within the Intelligent Systems Department and work on ML robustness, reliability and reasoning.
Read more about me here
News
C-RAG Certified Generation Risks for Retrieval-Augmented Language Models is accepted to ICML main conference!
Paper accepted at ICML 2024!
Data-centric Machine Learning Research -- Past, Present and Future
Check out our peer-reviewed position paper!
COLEP Certifiably Robust Learning-Reasoning Conformal Prediction via Probabilistic Circuits and Repeated Random Sampling for Minimizing the Time-to-Accuracy of Learning are accepted to ICLR main conference!
2 papers accepted at ICLR 2024!
I am serving as NeurIPS Affinity Events Chair this year!
Joined the NeurIPS Organization Team!
I'm appointed as the executive editor of the Journal of Data-centric Machine Learning Research (DMLR). Stay tuned for the call for papers!
DMLR Journal
Knowledge and Logical Reasoning Workshop will take place on 28 July 2023 in Hawaii.
Workshop at ICML 2023
Data-centric ML Research Workshop will take place on 29 July 2023 in Hawaii.
Workshop at ICML 2023
The report is out! I am delighted to a contributor since 2022.
AI Index Report 2023
I successfully defended my PhD thesis at ETH Zurich and accepted a faculty position at TU Delft!
Faculty position at TU Delft
I'm named one of the 2021 Google Academic Scholarship recipients!
Google Scholarship
Knowledge Enhanced Machine Learning Pipeline against Diverse Adversarial Attacks is accepted to ICML 2021!
Paper at ICML 2021
DeGNN Improving graph neural networks with graph decomposition and Fives Feature interaction via edge search for large scale tabular data accepted for publication at KDD 2021
Two papers accepted at KDD 2021
I'm elected as the vice president of the WiML organization, and will chair all WiML events until the spring of 2023.
New role as WiML VP
Online Active Model Selection for Pre-trained Classifiers is accepted to AISTATS 2021!