Maksim Zhdanov
I'm a Research Scientist at Tinkoff.
At the moment, I'm a 2-year BSc computer science student at University of Science and Technology MISIS (Moscow).
My passion is the AI research. I believe that the state-of-the-art technologies will shape our tomorrow as we continuosly understand the laws of our world better and better. Currently, I'm particularly interested in generative modeling, probabilistic methods, and geometric deep learning.
I'm also interested in AI4Science. Mostly in applications of machine learning to biomedical and physical systems.
In the past, I participated in numerous machine learning competitions. I'm a Kaggle Competitions Expert. In 2020, as a high school student, I took 2nd place in AI Journey Competition on computer vision which was focused on recognizing ancient manuscripts of Peter the Great.
In 2020, I recieved Open Data Science Best Speaker Award for the talk on my machine learning journey.
From cold Siberia
Links
[GitHub, Google Scholar, CV, LinkedIn, Research Gate]
Papers
Unveiling Empirical Pathologies of Laplace Approximation for Uncertainty Estimation
M. Zhdanov, S. Dereka, S. Kolesnikov
Association for the Advancement of Artificial Intelligence (AAAI) Deployable AI Workshop, 2024, Vancouver 🇨🇦
[PDF, ArXiv]
Diversifying Deep Ensembles: A Saliency Map Approach for Enhanced OOD Detection, Calibration, and Accuracy
S. Dereka, I. Karpukhin, M. Zhdanov, S. Kolesnikov
Pre-Print, 2023
[PDF, ArXiv]
Catching Image Retrieval Generalization
M. Zhdanov, I. Karpukhin
Pre-Print, 2023
[PDF, ArXiv]
Machine learning-assisted close-set X-ray diffraction phase identification of transition metals
M. Zhdanov, A. Zhdanov
International Conference on Learning Representations (ICLR) ML4Materials Workshop, 2023, Kigali 🇷🇼
[PDF, ArXiv,
Poster, Code]
Invited Talks
2023, MISIS.
2023, Tinkoff STEM University.
News
02/2024: I'm joining Tinkoff Research as a Research Scientist!
12/2023: Our paper on Laplace approximation is accepted to AAAI 2024 DAI Workshop. Stay tuned for updates!
10/2023: I gave a talk about our paper on deep ensembles in MISIS (in Russian).
10/2023: Pre-print of our paper on the diversification of deep ensembles is available.
07/2023: I gave a talk on the presentation day of Tinkoff STEM University.
06/2023: Pre-print of our paper on image retrieval generalization is available.
04/2023: MISIS media highlighted our paper.
03/2023: Our paper on machine learning for X-Ray diffraction is accepted to ICLR 2023
ML4Materials workshop.
01/2023: I'm starting my research internship at Tinkoff AI Lab.
