Hey, I'm Giorgos Nikolaou !

MSc in Data Science, EPFL • Researcher at GLADIA & TML

About Me

I'm currently living in Lausanne 🇨🇭, pursuing my MSc in Data Science at EPFL, after completing my BSc in Computer Science at the University of Athens. When I'm not buried in assignments, you can find me swimming, experimenting with new recipes, or catching up on some much-needed sleep. In my research, I'm interested in understanding the structure of representations and exploring AI safety, particularly machine unlearning.

Representation Learning Machine Unlearning AI Safety

Selected

Publications

Language Models are Injective and Hence Invertible

ICLR 2026

Giorgos Nikolaou*, Tommaso Mencattini*,
Donato Crisostomi, Andrea Santilli, Yannis Panagakis, Emanuele Rodolà

Experience

Research Student

Theory of Machine Learning Lab (TML), EPFL

PI: Nicolas Flammarion

Oct 2025 - Present
  • Conducting research on LLM machine unlearning, leveraging hidden representations to quantify token importance for targeted forgetting.
  • Developing token-importance-weighted loss functions and expanded benchmarking suites for the open-unlearning library, with the goal of submitting a PR to integrate these contributions.

Research Assistant

GLADIA, Sapienza Università di Roma

PI: Emanuele Rodolà

Aug 2025 - Present
  • Formally proved that LLMs are almost surely injective and used this insight to develop the first exact model inversion algorithm; see the preprint.
  • Ongoing research examines how representations can be leveraged to infer model behavior.

Data Science Internship

Logmind

Jul 2025 - Jan 2026
  • Optimized and scaled the log-based anomaly detection pipeline to support 200x data volume without degrading performance.
  • Prototyped an LLM-driven system for automated log analysis, generating actionable insights to streamline incident response.

Research Assistant

Archimedes Research Unit

PI: Yannis Panagakis

Jan 2025 - Mar 2025
  • Research on conditional image synthesis, leveraging multi-attribute embeddings for interpretable image-to-image translation.
  • Applied multi-modal learning techniques to enhance the performance and flexibility of generative architectures.

Data Engineering Internship

INNOV-ACTS

Mar 2024 - Aug 2024
  • Built optimized data-processing pipelines to extract, transform, and validate multi-organization data for the EuroHyPerCon project.
  • Developed automation scripts that streamlined data-integration workflows and delivered clear, actionable analytical outputs.

Education

Master of Science in Data Science

École Polytechnique Fédérale de Lausanne (EPFL)

2024 - Present
  • Maintaining a strong GPA of 5.68/6.
  • Completed advanced coursework in Measure-Theoretic Probability, Statistics, Optimization Theory, and Deep & Reinforcement Learning.

Bachelor of Science in Computer Science

National and Kapodistrian Univeristy of Athens

2020 - 2024
  • Graduated with distinction, earning a GPA of 9.18/10.
  • Thesis selected among the department's best Bachelor's and Master's theses (2024 cohort).
  • Thesis: "Higher-Order Deep Unfolding Networks for Compressed Sensing"
    Supervisor: Yannis Panagakis
    Developed a deep unfolding network for compressed sensing leveraging proximal algorithms within the Augmented Lagrangian framework, integrating a novel higher-order polynomial module to enhance model expressiveness. Achieved state-of-the-art reconstruction performance with over 3dB PSNR improvement at ultra-low sampling rates (1-10%).

News

Jan 26, 2026
Our paper "Language Models are Injective and Hence Invertible" was accepted at ICLR 2026!
Nov 27, 2025
Invited talk on LLM injectivity and invertibility at the Laboratory of Data Engineering of Area Science Park, where we presented and discussed our recent work. Many thanks to Alberto Cazzaniga and Diego Doimo for the invitation and warm hospitality!
Oct 17, 2025
Preprint Alert: Language Models Are Injective and Hence Invertible. We prove that LLMs are injective, empirically stress-test this property, and develop the first inversion algorithm with theoretical guarantees. To top it off, the announcement went viral on (≈5M views)!
Jul 07, 2025
Excited to begin my Data Science Intersnhsip at Logmind!
Jun 27, 2025
Honored to have received the Bodossaki Foundation Graduate Scholarship to support my graduate studies at EPFL.
May 25, 2025
My undergraduate thesis was selected for publication among the department's best Bachelor's and Master's theses for 2024!
Jul 04, 2024
Grateful to have been awarded the "SYN-ENOSIS for Education Scholarship" by the Union of Greek Shipowners, supporting my graduate studies at EPFL.