Zhakshylyk Nurlanov

Zhakshylyk Nurlanov

AI Researcher

University of Bonn

Bosch Center for AI

About me

Hi, there!👋 I am a PhD student specializing in AI Security and Safety. Previously, I have developed reliable AI systems and contributed to cutting-edge projects at Bosch, TUM, and Samsung, with research published in top-tier venues. My expertise lies in training robust models, designing problem-specific optimization methods, and advancing computer vision techniques. Now, I am eager to leverage these skills to develop interpretable and trustworthy AI solutions that drive scientific discovery and address complex interdisciplinary challenges.

Interests
  • AI Security and Safety
  • Computer Vision
  • Optimization
  • Scientific Discovery with AI
Education
  • PhD in Artificial Intelligence, 2025

    University of Bonn

  • MSc in Computer Science, 2021

    Technical University of Munich

  • BSc in Applied Mathematics and Physics, 2019

    Moscow Institute of Physics and Technology

Publications

Adaptive Certified Training: Towards Better Accuracy-Robustness Tradeoffs
Zhakshylyk Nurlanov, Frank R. Schmidt, Florian Bernard. In ECML PKDD 2024
Adaptive Certified Training: Towards Better Accuracy-Robustness Tradeoffs
Universe Points Representation Learning for Partial Multi-Graph Matching
Zhakshylyk Nurlanov, Frank R. Schmidt, Florian Bernard. In AAAI 2023 (Oral Presentation)
Universe Points Representation Learning for Partial Multi-Graph Matching
Efficient and Flexible Sublabel-Accurate Energy Minimization
Zhakshylyk Nurlanov, Daniel Cremers, Florian Bernard. In ICPR 2022
Efficient and Flexible Sublabel-Accurate Energy Minimization
Fully Event-Based Visual Odometry
Zhakshylyk Nurlanov, Nikita Korobov. Technical Report 2020
Fully Event-Based Visual Odometry

Patents

(2023). Device and Computer Implemented Method for Machine Learning.

EP

(2022). Robust Tracking of Keypoints of Objects in Images.

DE

(2019). Method for Generating Head Model Animation From Voice Signal, and Electronic Device for Implementing Same.

WO KR RU