Aryan Ahadinia

About Me

I am a master of computer science student at IC, EPFL, and a research assistant at the ETH/EPFL AI Center (Swiss AI Initiative), where I work on inference and infrastructure of the Apertus LLM project. I have recently completed a six month internship at Oracle Labs Switzerland, working on AgentSpec and WayFlow, Oracle’s open-source libraries for building agentic workflows. I had done a semester research project at INDY, EPFL on Bayesian Optimization with Dr. Anthony Bardou and Prof. Dr. Patrick Thiran, published at ICLR 2026. I also worked on Deep Equilibrium models as student research assistant at EPFL. Previously, I completed my bachelor’s degree in Computer Engineering at Sharif University of Technology and done my thesis on graph mining in social networks under supervision of Prof. Dr. Maryam Ramezani.

Research Interests

In a nutshell, I am interested in Machine Learning and Data Mining. More specifically:

LLM Inference & Infrastructure: At the ETH/EPFL AI Center, I work on high-performance LLM serving and deployment infrastructure for the Apertus LLM project, on the CSCS Alps supercomputing infrastructure.
LLMs/Agents: During my internship at Oracle Labs, I have worked on different aspects of building, using, and evaluating LLMs/Agents with reasoning capability.
Bayesian Optimization: As a semester project at EPFL, I have worked on encoding invariance in BO for more efficient BO with lower regret bound (ICLR ‘26).
Graph Mining, Social Networks: During my bachelors, I have worked on graph mining in the context of social networks. We were particularly interested in applying probabilistic models on time-series data to discover hidden spatial and temporal relations in Social Media (arXiv ‘23, Scientific Reports ‘24).

Education

M.Sc. in Computer Science, École polytechnique fédérale de Lausanne (EPFL), 2024 - present.
B.Sc. in Computer Engineering, Sharif University of Technology, 2019 - 2023.

News

[February 2026] Joining the ETH/EPFL AI Center (Swiss AI Initiative) as a research assistant, working on inference and infrastructure of the Apertus LLM project!
[January 2026] Our paper “Symmetry-Aware Bayesian Optimization via Max Kernels” is accepted at ICLR ‘26! This paper was the outcome of my semester project at INDY, EPFL, under supervision of Dr. Anthony Bardou and Prof. Dr. Patrick Thiran.
[January 2026] Happy to conclude my six month internship at Oracle!
[October 2025] Oracle has open-sourced agent-spec and wayflow for building agents! Proud to be a very small part of this project during my internship!
[July 2025] Starting a six month internship at Oracle Labs Switzerland! Excited to work on LLMs/agents there!
[September 2024] Starting master of Computer Science at EPFL!
[September 2023] Graduated from Department of Computer Engineering, Sharif University of Technology!

Publications

ICLR

Symmetry-Aware Bayesian Optimization via Max Kernels

Anthony Bardou, Antoine Gonon, Aryan Ahadinia, Patrick Thiran

The Fourteenth International Conference on Learning Representations (ICLR), 2026

PDF Project Page

Scientific Reports

DANI: Fast Diffusion Aware Network Inference with Preserving Topological Structure Property

Maryam Ramezani, Aryan Ahadinia, Erfan Farhadi, and Hamid R. Rabiee

Nature Scientific Reports volume 14, Article number: 31053 (2024)

PDF Code Project Page

arXiv

Joint Inference of Diffusion and Structure in Partially Observed Social Networks Using Coupled Matrix Factorization

Maryam Ramezani, Aryan Ahadinia, Amirmohammad Ziaei Bideh, and Hamid R. Rabiee

arXiv preprint arXiv:2010.01400, 2023

PDF Code Project Page