Publications

Zhakshylyk Nurlanov, Frank R. Schmidt, Florian Bernard (2025). Jailbreaking LLMs Without Gradients or Priors: Effective Transferable Attacks via Random Local Search. Preprint 2025.

Zhakshylyk Nurlanov, Frank R. Schmidt, Florian Bernard (2024). Adaptive Certified Training: Towards Better Accuracy-Robustness Tradeoffs. In ECML PKDD 2024.

PDF Cite Code DOI

Zhakshylyk Nurlanov, Frank R. Schmidt, Florian Bernard (2023). Universe Points Representation Learning for Partial Multi-Graph Matching. In AAAI 2023 (Oral Presentation).

Zhakshylyk Nurlanov, Daniel Cremers, Florian Bernard (2022). Efficient and Flexible Sublabel-Accurate Energy Minimization. In ICPR 2022.

PDF Cite Code DOI

Zhakshylyk Nurlanov (2021). Exploring SO(3) Logarithmic Map: Degeneracies and Derivatives. Technical Report 2021.

Zhakshylyk Nurlanov, Nikita Korobov (2020). Fully Event-Based Visual Odometry. Technical Report 2020.