Andrei Manolache

IMPRS-IS and ELLIS PhD Student. ML Researcher at Bitdefender. Interested in robust & trustworthy Geometric Deep Learning. 🇷🇴 ➡️ 🇩🇪

prof_pic.jpg

Hi there 👋! I’m Andrei, I am currently a Ph.D. candidate at the International Max Planck Research School for Intelligent Systems and ELLIS, under the co-supervision of Mathias Niepert (University of Stuttgart) and Karsten Borgwardt (ETH Zürich & MPI-B). I am also a Machine Learning Researcher at Bitdefender’s Theoretical Research Laboratory. I got a B.Sc. in Mathematics and a M.Sc. in Artificial Intelligence from the University of Bucharest. In the past I have also worked as a Software Engineer for NXP Semiconductors.

I’ve served as a reviewer for EMNLP 2022 and NeurIPS 2022

My Ph.D. research focuses on the design and development of Geometric Deep Learning methods where the robustness and trustworthiness of such models are an integral part of the research. My Master’s thesis involved deep anomaly detection in text (full thesis).

news

Oct 6, 2022 One short paper accepted at EMNLP 2022! 🤩
Oct 4, 2022 I became a Ph.D. candidate at the University of Stuttgart! 🎉
Jul 16, 2022 Two papers accepted (VeriDark & AnoShift) at the NeurIPS Datasets & Benchmarks track! 🤩
Jul 6, 2022 I attended the 2022 edition of the East European Summer School as a Teaching Assistant!
Jul 23, 2021 I presented our paper, DATE: Detecting Anomalies in Text via Self-Supervision of Transformers at the ICML 2021 UDL Workshop!
Jul 7, 2021 I attended the 2021 edition of the East European Summer School as a Participant and won a Best Poster award!
Jun 6, 2021 I presented our paper, DATE: Detecting Anomalies in Text via Self-Supervision of Transformers at NAACL 2021!
Jun 1, 2021 I got my Master’s degree from the University of Bucharest! (Thesis)
May 7, 2021 Me and my team from the University of Bucharest have won the 1st prize at the ICLR 2021 Computational Geometry & Topology Challenge!
Aug 25, 2020 Me and my team have won the 1st prize at the 2020 PyTorch Summer Hackaton with our healthcare assistant, https://devpost.com/software/pytorchxai!

selected publications

  1. EMNLP22
    Rethinking the Authorship Verification Experimental Setups
    Florin Brad, Andrei Manolache, Elena Burceanu, and 3 more authors
    Dec 2022
  2. NeurIPS22
    VeriDark: A Large-Scale Benchmark for Authorship Verification on the Dark Web
    Andrei Manolache, Florin Brad, Antonio Barbalau, and 2 more authors
    Dec 2022
  3. NeurIPS22
    AnoShift: A Distribution Shift Benchmark for Unsupervised Anomaly Detection
    Marius Drăgoi, Elena Burceanu, Emanuela Haller, and 2 more authors
    Dec 2022
  4. NAACL21
    DATE: Detecting Anomalies in Text via Self-Supervision of Transformers
    Andrei Manolache, Florin Brad, and Elena Burceanu
    In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies Jun 2021