Nurbek Tastan

nurbek.tastan@mbzuai.ac.ae

Abu Dhabi, UAE

I am Nurbek Tastan, a PhD candidate in Machine Learning at MBZUAI, affiliated with the SPriNT-AI lab. I conduct my research under the guidance of Dr. Karthik Nandakumar and Dr. Samuel Horvath.

My research focuses on trustworthy and efficient machine learning, with particular emphasis on incentivization, privacy, robustness, and efficiency in collaborative settings. I also develop methods to make large-scale models, including large language models, more efficiently fine-tunable while also preserving utility and confidentiality.

Currently expanding my research toward agentic AI and LLMs, with a focus on the trustworthiness and efficiency of such systems.

Passionate about building machine learning systems that are not only performant, but also equitable, privacy-aware, and computationally viable for real-world deployment.

news

Feb, 2026	Our paper SPDMark was accepted at CVPR 2026.
Jan, 2026	Three of our papers were accepted at ICLR 2026: SelfOrg, LoFT, and MOLM.
Oct, 2025	Our paper A Framework for Double-Blind Federated Adaptation of Foundation Models was accepted at ICCV 2025.
Jul, 2025	Our paper Aequa: Fair Model Rewards in Collaborative Learning via Slimmable Networks was accepted at ICML 2025.
Jul, 2025	Our paper CYCle: Choosing Your Collaborators Wisely to Enhance Collaborative Fairness in Decentralized Learning was accepted at TMLR.

selected publications

ICLR

Stochastic Self-Organization in Multi-Agent Systems

Nurbek Tastan, Samuel Horváth, and Karthik Nandakumar

In The Fourteenth International Conference on Learning Representations, 2026

Bib PDF Code OpenReview

@inproceedings{tastan2026stochastic,
  title = {Stochastic Self-Organization in Multi-Agent Systems},
  author = {Tastan, Nurbek and Horv{\'a}th, Samuel and Nandakumar, Karthik},
  booktitle = {The Fourteenth International Conference on Learning Representations},
  year = {2026},
  url = {https://openreview.net/forum?id=rS3Jb9AAej},
}

ICLR

LoFT: Low-Rank Adaptation That Behaves Like Full Fine-Tuning

Nurbek Tastan, Stefanos Laskaridis, Martin Takáč, Karthik Nandakumar, and Samuel Horváth

In The Fourteenth International Conference on Learning Representations, 2026

Bib PDF Code OpenReview

@inproceedings{tastan2026loft,
  title = {{Lo{FT}: Low-Rank Adaptation That Behaves Like Full Fine-Tuning}},
  author = {Tastan, Nurbek and Laskaridis, Stefanos and Tak{\'a}{\v{c}}, Martin and Nandakumar, Karthik and Horv{\'a}th, Samuel},
  booktitle = {The Fourteenth International Conference on Learning Representations},
  year = {2026},
  url = {https://openreview.net/forum?id=86P3sb1dpr},
}

ICCV

A Framework for Double-Blind Federated Adaptation of Foundation Models

Nurbek Tastan, and Karthik Nandakumar

In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), ICLR 2025 Workshop on Modularity for Collaborative, Decentralized, and Continual Deep Learning (MCDC), 2025

Bib PDF Code Poster OpenReview

@inproceedings{tastan2025framework,
  title = {{A Framework for Double-Blind Federated Adaptation of Foundation Models}},
  author = {Tastan, Nurbek and Nandakumar, Karthik},
  booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), ICLR 2025 Workshop on Modularity for Collaborative, Decentralized, and Continual Deep Learning (MCDC)},
  year = {2025},
  url = {https://openreview.net/forum?id=stv0Fqxekz},
}

TMLR

CYCle: Choosing Your Collaborators Wisely to Enhance Collaborative Fairness in Decentralized Learning

Nurbek Tastan, Samuel Horváth, and Karthik Nandakumar

Transactions on Machine Learning Research, 2025

Bib PDF Code OpenReview

@article{tastan2025cycle,
  title = {{{CYC}le: Choosing Your Collaborators Wisely to Enhance Collaborative Fairness in Decentralized Learning}},
  author = {Tastan, Nurbek and Horv{\'a}th, Samuel and Nandakumar, Karthik},
  journal = {Transactions on Machine Learning Research},
  issn = {2835-8856},
  year = {2025},
  url = {https://openreview.net/forum?id=ygqNiLQqfH},
  note = {},
}

ICML

Aequa: Fair Model Rewards in Collaborative Learning via Slimmable Networks

Nurbek Tastan, Samuel Horváth, and Karthik Nandakumar

In Proceedings of the Forty-second International Conference on Machine Learning (ICML), 2025

Bib PDF Code OpenReview

@inproceedings{tastan2025aequa,
  title = {{Aequa: Fair Model Rewards in Collaborative Learning via Slimmable Networks}},
  author = {Tastan, Nurbek and Horv\'{a}th, Samuel and Nandakumar, Karthik},
  year = {2025},
  url = {https://openreview.net/forum?id=Tw81RElDpe},
  booktitle = {Proceedings of the Forty-second International Conference on Machine Learning (ICML)},
  series = {Proceedings of Machine Learning Research},
}