Nikolaos Dimitriadis

PhD student, EPFL - EPF Lausanne

Joined

May 2022

Names

Nikolaos Dimitriadis (Preferred)

Emails

****@gmail.com (Confirmed)

****@epfl.ch (Confirmed)

Personal Links

Homepage

Google Scholar

DBLP

Career & Education History

PhD student

EPFL - EPF Lausanne (epfl.ch)

2020 – Present

Intern

Google DeepMind (google.com)

2023 – 2025

Undergrad student

National Technical University of Athens (ntua.gr)

2014 – 2020

Advisors, Relations & Conflicts

PhD Advisor

Francois Fleuret

2020 – Present

PhD Advisor

Pascal Frossard

2020 – Present

Expertise

No areas of expertise listed

Publications

Model soups need only one ingredient
Alireza Abdollahpoorrostam, Nikolaos Dimitriadis, Adam Hazimeh, Pascal Frossard
- Submitted to ICLR 2026
- Readers: Everyone
LiNeS: Post-training Layer Scaling Prevents Forgetting and Enhances Model Merging
Ke Wang, Nikolaos Dimitriadis, Alessandro Favero, Guillermo Ortiz-Jimenez, François Fleuret, Pascal Frossard
- Greeks in AI 2025 Oral
- Readers: Everyone
Pareto Low-Rank Adapters: Efficient Multi-Task Learning with Preferences
Nikolaos Dimitriadis, Pascal Frossard, François Fleuret
- Greeks in AI 2025 Oral
- Readers: Everyone
MEMOIR: Lifelong Model Editing with Minimal Overwrite and Informed Retention for LLMs
Ke Wang, Yiming QIN, Nikolaos Dimitriadis, Alessandro Favero, Pascal Frossard
- NeurIPS 2025 poster
- Readers: Everyone
Pareto Low-Rank Adapters: Efficient Multi-Task Learning with Preferences
Nikolaos Dimitriadis, Pascal Frossard, François Fleuret
- ICLR 2025 Poster
- Readers: Everyone
LiNeS: Post-training Layer Scaling Prevents Forgetting and Enhances Model Merging
Ke Wang, Nikolaos Dimitriadis, Alessandro Favero, Guillermo Ortiz-Jimenez, François Fleuret, Pascal Frossard
- ICLR 2025 Poster
- Readers: Everyone
Localizing Task Information for Improved Model Merging and Compression
Ke Wang, Nikolaos Dimitriadis, Guillermo Ortiz-Jimenez, François Fleuret, Pascal Frossard
- ICML 2024 Poster
- Readers: Everyone
Benefits of Max Pooling in Neural Networks: Theoretical and Experimental Evidence
Kyle Matoba, Nikolaos Dimitriadis, François Fleuret
- Accepted by TMLR
- Readers: Everyone
Pareto Manifold Learning: Tackling multiple tasks via ensembles of single-task models
Nikolaos Dimitriadis, Pascal Frossard, François Fleuret
- ICML 2023 Poster
- Readers: Everyone
Flexible Channel Dimensions for Differentiable Architecture Search
Ahmet Caner Yüzügüler, Nikolaos Dimitriadis, Pascal Frossard
- CoRR 2023
- Readers: Everyone

View all 20 publications

Nikolaos Dimitriadis

Names

Emails

Personal Links

Career & Education History

Advisors, Relations & Conflicts

Expertise

Publications

Co-Authors