A.A. Gde Yogi Pramana

I’m currently an AI Safety Research Associate at AI Singapore, NTU, and an incoming CS PhD student at the National University of Singapore (NUS).

My research spans AI safety, AI alignment, and cooperative AI: making models robust under adversarial pressure, aligning them with human intent beyond the training distribution, and studying how AI systems and people can coordinate without one party’s goals overriding everyone else’s. That last problem is why I believe the future of AI will be pluralistic — human values are plural and often incompatible, so alignment should treat disagreement as a design constraint rather than as noise to be averaged away.

I hold a Master of Computing in Artificial Intelligence from NUS (2026), a Bachelor of Computing from BINUS University (2026), and a Bachelor of Science from Universitas Gadjah Mada (2025).

selected publications

arXiv

SafeMed-R1: Adversarial Reinforcement Learning for Generalizable and Robust Medical Reasoning in Vision-Language Models

A.A. Gde Yogi Pramana, J. Ray, A. Jaya, and 1 more author

arXiv preprint arXiv:2512.19317, 2025

arXiv Bib

@article{pramana2025safemedr1,
  title = {SafeMed-R1: Adversarial Reinforcement Learning for Generalizable and Robust Medical Reasoning in Vision-Language Models},
  author = {Pramana, A.A. Gde Yogi and Ray, J. and Jaya, A. and Wijaya, M.},
  journal = {arXiv preprint arXiv:2512.19317},
  year = {2025},
}

ICCoSITE

ESDS: AI-powered early stunting detection and monitoring system using edited radius-SMOTE algorithm

A.A. Gde Yogi Pramana, H.M. Zidan, M.F. Maulana, and 1 more author

In Proceedings of the 2024 7th International Conference on Computational Intelligence and Intelligent Systems, 2024

Bib

@inproceedings{pramana2024esds,
  title = {ESDS: AI-powered early stunting detection and monitoring system using edited radius-SMOTE algorithm},
  author = {Pramana, A.A. Gde Yogi and Zidan, H.M. and Maulana, M.F. and Natan, O.},
  booktitle = {Proceedings of the 2024 7th International Conference on Computational Intelligence and Intelligent Systems},
  year = {2024},
}

IEEE CAI

Enhancing Early Stunting Detection: A Novel Approach using Artificial Intelligence with an Integrated SMOTE Algorithm and Ensemble Learning Model

A.A. Gde Yogi Pramana, M.F. Maulana, M.C. Tirtayasa, and 1 more author

In 2024 IEEE Conference on Artificial Intelligence (CAI), 2024

Bib

@inproceedings{pramana2024stunting,
  title = {Enhancing Early Stunting Detection: A Novel Approach using Artificial Intelligence with an Integrated SMOTE Algorithm and Ensemble Learning Model},
  author = {Pramana, A.A. Gde Yogi and Maulana, M.F. and Tirtayasa, M.C. and Tyas, D.A.},
  booktitle = {2024 IEEE Conference on Artificial Intelligence (CAI)},
  pages = {486--493},
  year = {2024},
}