personal website

Andrei Manolache

IMPRS-IS and ELLIS PhD Student. ML Researcher at Bitdefender. Interested in how deep learning models acquire useful inductive biases, especially equivariance, and how we can control them reliably. 🇷🇴 -> 🇩🇪

Andrei Manolache
profile.jpg
about.txt

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, ICML 2022/2023/2024/2026, NeurIPS 2022/2023/2024/2025. I got a Best Reviewer award for NeurIPS 2022, 2023 and 2024, and was named a Gold Reviewer at ICML 2026.

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.log
  1. I was named a Gold Reviewer at ICML 2026!
  2. Two papers accepted at ICML 2026! Protein Fold Classification at Scale: Benchmarking and Pretraining was accepted as an Oral, and Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining was accepted as a Poster.
  3. One paper accepted at the ICML 2026 Workshop on Weight-Space Symmetries: How the Optimizer Shapes Learned Solutions in Equivariant Neural Networks.
  4. Our paper, Learning (Approximately) Equivariant Networks via Constrained Optimization has been accepted as an Oral 📢 at NeurIPS 2025! I will also be presenting the paper at the NeurIPS NPGML workshop and at the COML workshop.
  5. Two workshop papers accepted at NeurIPS 2025! Come talk with us about Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining at the NPGML Workshop, and ChronoGraph: A Real-World Graph-Based Multivariate Time Series Dataset at the BERT2S Workshop!
  6. I will be attending the 2025 edition of the East European Summer School - ping me if you'd like to have a coffee :).
  7. One paper on Rewiring and Virtual Nodes at NeurIPS 2024!
  8. I got a Best Reviewer award at NeurIPS 2024!
  9. I attended the 2024 edition of the East European Summer School as a Teaching Assistant and an Industry Speaker! My keynote talk for Bitdefender is available here.
  10. One paper on Graph Rewiring at ICLR 2024 🤩!
  11. I got a Best Reviewer award at NeurIPS 2023!
  12. One long paper at EMNLP 2023! ✨
  13. One paper at the ICDM 2023 AI for Time Series workshop!
  14. One paper at the ICML 2023 Differentiable Almost Everything workshop!
  15. One short paper accepted at EMNLP 2022! 🤩
  16. I became a Ph.D. candidate at the University of Stuttgart! 🎉
  17. Two papers accepted (VeriDark & AnoShift) at the NeurIPS Datasets & Benchmarks track! 🤩
  18. I attended the 2022 edition of the East European Summer School as a Teaching Assistant!
  19. I presented our paper, DATE: Detecting Anomalies in Text via Self-Supervision of Transformers at the ICML 2021 UDL Workshop!
  20. I attended the 2021 edition of the East European Summer School as a Participant and won a Best Poster award!
  21. I presented our paper, DATE: Detecting Anomalies in Text via Self-Supervision of Transformers at NAACL 2021!
  22. I got my Master's degree from the University of Bucharest! (Thesis)
  23. Me and my team from the University of Bucharest have won the 1st prize at the ICLR 2021 Computational Geometry & Topology Challenge!
  24. Me and my team have won the 1st prize at the 2020 PyTorch Summer Hackaton with our healthcare assistant, Q&Aid!
selected-papers.ini
  1. ICML26 Oral Protein Fold Classification at Scale: Benchmarking and Pretraining
    Dexiong Chen*, Andrei Manolache*, Mathias Niepert, Karsten Borgwardt.
  2. ICML26 Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining
    Boshra Ariguib, Mathias Niepert, Andrei Manolache.
  3. ICML26 WSS How the Optimizer Shapes Learned Solutions in Equivariant Neural Networks
    Teodor-Mihai Stupariu, Andrei Manolache.
  4. NeurIPS25 Oral Learning (Approximately) Equivariant Networks via Constrained Optimization
    Andrei Manolache, Luiz F. O. Chamon, Mathias Niepert.
  5. NeurIPS25 BERT2S ChronoGraph: A Real-World Graph-Based Multivariate Time Series Dataset
    Luțu Adrian-Cătălin, Ioana Pintilie, Elena Burceanu, Andrei Manolache.
  6. NeurIPS24 Probabilistic Graph Rewiring via Virtual Nodes
    Chendi Qian*, Andrei Manolache*, Christopher Morris, Mathias Niepert.
  7. ICLR24 Probabilistically Rewired Message-Passing Neural Networks
    Chendi Qian*, Andrei Manolache*, Kareem Ahmed, Zhe Zeng, Guy Van den Broeck, Mathias Niepert, Christopher Morris.
  8. EMNLP23 AD-NLP: A Benchmark for Anomaly Detection in Natural Language Processing
    Matei Bejan*, Andrei Manolache*, Marius Popescu.
  9. EMNLP22 Rethinking the Authorship Verification Experimental Setups
    Florin Brad*, Andrei Manolache*, Elena Burceanu, Antonio Barbalau, Radu Tudor Ionescu, Marius Popescu.
  10. NeurIPS22 VeriDark: A Large-Scale Benchmark for Authorship Verification on the Dark Web
    Andrei Manolache*, Florin Brad*, Antonio Barbalau, Radu Tudor Ionescu, Marius Popescu.
  11. NeurIPS22 AnoShift: A Distribution Shift Benchmark for Unsupervised Anomaly Detection
    Marius Drăgoi, Elena Burceanu, Emanuela Haller, Andrei Manolache, Florin Brad.
  12. NAACL21 DATE: Detecting Anomalies in Text via Self-Supervision of Transformers
    Andrei Manolache, Florin Brad, Elena Burceanu.
publications.db

2026

  1. ICML26 Oral Protein Fold Classification at Scale: Benchmarking and Pretraining
    Dexiong Chen*, Andrei Manolache*, Mathias Niepert, Karsten Borgwardt. The Forty-third International Conference on Machine Learning.
  2. ICML26 Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining
    Boshra Ariguib, Mathias Niepert, Andrei Manolache. The Forty-third International Conference on Machine Learning.
  3. ICML26 WSS How the Optimizer Shapes Learned Solutions in Equivariant Neural Networks
    Teodor-Mihai Stupariu, Andrei Manolache. ICML 2026 Workshop on Weight-Space Symmetries.

2025

  1. NeurIPS25 Oral Learning (Approximately) Equivariant Networks via Constrained Optimization
    Andrei Manolache, Luiz F. O. Chamon, Mathias Niepert. The Thirty-ninth Annual Conference on Neural Information Processing Systems.
  2. NeurIPS25 BERT2S ChronoGraph: A Real-World Graph-Based Multivariate Time Series Dataset
    Luțu Adrian-Cătălin, Ioana Pintilie, Elena Burceanu, Andrei Manolache. Recent Advances in Time Series Foundation Models Have We Reached the 'BERT Moment'?

2024

  1. NeurIPS24 Probabilistic Graph Rewiring via Virtual Nodes
    Chendi Qian*, Andrei Manolache*, Christopher Morris, Mathias Niepert. The Thirty-eighth Annual Conference on Neural Information Processing Systems.
  2. ICLR24 Probabilistically Rewired Message-Passing Neural Networks
    Chendi Qian*, Andrei Manolache*, Kareem Ahmed, Zhe Zeng, Guy Van den Broeck, Mathias Niepert, Christopher Morris.

2023

  1. EMNLP23 AD-NLP: A Benchmark for Anomaly Detection in Natural Language Processing
    Matei Bejan*, Andrei Manolache*, Marius Popescu. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing.
  2. ICML23 DiffAlmostEverything Probabilistic Task-Adaptive Graph Rewiring
    Chendi Qian*, Andrei Manolache*, Kareem Ahmed, Zhe Zeng, Guy Van den Broeck, Mathias Niepert, Christopher Morris. ICML 2023 Workshop on Differentiable Almost Everything.
  3. ICDM23 AI4TS Time Series Anomaly Detection using Diffusion-based Models
    Ioana Pintilie, Andrei Manolache, Florin Brad. ICDM 2023 AI for Time Series Workshop.

2022

  1. EMNLP22 Rethinking the Authorship Verification Experimental Setups
    Florin Brad*, Andrei Manolache*, Elena Burceanu, Antonio Barbalau, Radu Tudor Ionescu, Marius Popescu.
  2. NeurIPS22 VeriDark: A Large-Scale Benchmark for Authorship Verification on the Dark Web
    Andrei Manolache*, Florin Brad*, Antonio Barbalau, Radu Tudor Ionescu, Marius Popescu. Proceedings of the 36th Conference on Neural Information Processing Systems, Datasets and Benchmarks Track.
  3. NeurIPS22 AnoShift: A Distribution Shift Benchmark for Unsupervised Anomaly Detection
    Marius Drăgoi, Elena Burceanu, Emanuela Haller, Andrei Manolache, Florin Brad. Proceedings of the 36th Conference on Neural Information Processing Systems, Datasets and Benchmarks Track.

2021

  1. NAACL21 DATE: Detecting Anomalies in Text via Self-Supervision of Transformers
    Andrei Manolache, Florin Brad, Elena Burceanu. Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies.
  2. arXiv ICLR 2021 Challenge for Computational Geometry & Topology: Design and Results
    Nina Miolane, Matteo Caorsi, Umberto Lupo, Marius Guerard, Nicolas Guigui, Johan Mathe, Yann Cabanes, Wojciech Reise, Thomas Davies, António Leitão, Somesh Mohapatra, Saiteja Utpala, Shailja Shailja, Gabriele Corso, Guoxi Liu, Federico Iuricich, Andrei Manolache, and others.