Ayhan Suleymanzade

Hey there!

I am a Visiting Researcher at AITHYRA, supervised by Prof. Ismail Ilkan Ceylan and Prof. Michael Bronstein. I am also an incoming PhD student at EPFL. My research interests lie at the intersection of Generative Modeling, Large Language Models, and AI for Science. In particular, I am interested in continuous/implicit reasoning architectures, flow/diffusion models, and their applications in scientific domains such as molecular dynamics and drug discovery.

I completed my Bachelor’s degree in CS/EE at KAIST in South Korea, where I worked on Geometric Deep Learning, Generative Flow Networks (GFNs), and Deep Reinforcement Learning (DRL).

During my exchange semester at TUM, I was fortunate to work with Prof. Stefanie Jegelka.

Beyond research, I enjoy solving challenging physics problems and teaching others. I lead Team Azerbaijan at international physics olympiads, including IPhO and EuPhO.

I am always open to new research collaborations and opportunities. Feel free to check out my CV.

news

Feb 28, 2026	I graduated from KAIST with Summa Cum Laude honors, ranking 2nd out of 143 students in the Computer Science Department. 🎉
Nov 24, 2025	I am deeply humbled to receive the KAIST Q-Day Award 2025 [Advanced Research Division] in recognition of my contributions to academic research. 🎉
May 15, 2025	Our paper, CultDiff, has been accepted to ACL 2025 Main Conference as Oral Presentation! 🎉
Apr 16, 2025	I started my exchange semester at TU Munich, Germany. I am working with Prof. Stefanie Jegelka.
Feb 20, 2025	I am honored to be recognized on the Dean’s List for the Fall 2024 semester for the 4th time. 🎉
Feb 15, 2025	Our paper, Random Walk Neural Networks, has been accepted to ICLR 2025 as Spotlight Presentation! 🎉
Jan 10, 2025	I have started my internship at Mercari Inc, Japan.

Selected Publications

ICLR 2026 Workshop

MUX: Continuous Reasoning via Multiplexed Tokens

Ayhan Suleymanzade, Halil Alperen Gozeten, Michael Bronstein, and 2 more authors

ICLR 2026 Workshop on LLM Reasoning, 2026

Bib PDF Website

@article{suleymanzade2026mux,
  title = {{MUX}: Continuous Reasoning via Multiplexed Tokens},
  author = {Suleymanzade, Ayhan and Gozeten, Halil Alperen and Bronstein, Michael and Ceylan, İsmail İlkan and Kim, Jinwoo},
  year = {2026},
  journal = {ICLR 2026 Workshop on LLM Reasoning},
  eprint = {2607.18264},
  archiveprefix = {arXiv},
  primaryclass = {cs.AI},
  url = {https://arxiv.org/abs/2607.18264},
}

ACL 2025 Oral

Diffusion Models Through a Global Lens: Are They Culturally Inclusive?

Zahra Bayramli^*, Ayhan Suleymanzade^*, Na Min An, and 5 more authors

Association for Computational Linguistics (ACL), 2025

Bib PDF

@article{bayramli2025diffusionmodelsgloballens,
  title = {Diffusion Models Through a Global Lens: Are They Culturally Inclusive?},
  author = {Bayramli, Zahra and Suleymanzade, Ayhan and An, Na Min and Ahmad, Huzama and Kim, Eunsu and Park, Junyeong and Thorne, James and Oh, Alice},
  year = {2025},
  journal = {Association for Computational Linguistics (ACL)},
  oral = {Oral},
}

ICLR 2025 Spotlight

Revisiting Random Walks for Learning on Graphs

Jinwoo Kim, Olga Zaghen^*, Ayhan Suleymanzade^*, and 2 more authors

International Conference on Learning Representations (ICLR), 2025

Bib PDF

@article{kim2025revisitingrandomwalkslearning,
  title = {Revisiting Random Walks for Learning on Graphs},
  author = {Kim, Jinwoo and Zaghen, Olga and Suleymanzade, Ayhan and Ryou, Youngmin and Hong, Seunghoon},
  year = {2025},
  journal = {International Conference on Learning Representations (ICLR)},
  spotlight = {Spotlight},
}

NeurIPS 2023 Spotlight

Learning Probabilistic Symmetrization for Architecture Agnostic Equivariance

Jinwoo Kim, Tien Dat Nguyen, Ayhan Suleymanzade, and 2 more authors

Neural Information Processing Systems (NeurIPS), 2023

Bib PDF

@article{kimd2024learningprobabilisticsymmetrizationarchitecture,
  title = {Learning Probabilistic Symmetrization for Architecture Agnostic Equivariance},
  author = {Kim, Jinwoo and Nguyen, Tien Dat and Suleymanzade, Ayhan and An, Hyeokjun and Hong, Seunghoon},
  year = {2023},
  journal = {Neural Information Processing Systems (NeurIPS)},
  spotlight = {Spotlight},
}