Nour Shaheen

Nour Shaheen

I just finished my master’s degree in computer engineering at Polytechnique Montréal and at Mila. I graduated with excellence and was nominated for the best thesis award. My research interests include optimization and deep learning dynamics, tabular foundation models, and model merging techniques. I graduated third in my class with honors from Alexandria University and interned at Microsoft, MBZUAI, and the Applied Innovation Center.

Nour Shaheen

I was elected and am currently serving as a Lab Representative at Mila for the year 2025/2026.

In my free time, I enjoy writing poetry, playing the drums 🥁, and discovering the beautiful city of Montréal.

I care A LOT about making research a more welcoming place for people from underrepresented groups, and I’m always happy to chat with anyone figuring out their own path.

Contact me (no spaces):

nourheshamshaheen [AT] gmail [DOT] com

nour [DOT] shaheen [AT] mila [DOT] quebec

Publications

  1. OOD TFM paper

    Understanding the Surprising Generalization Properties of Tabular Foundation Models

    Nour Shaheen*, Junwei Ma*, Alex Labach, Frank Hutter, Valentin Thomas, Anthony L. Caterini.

    Accepted at NeurIPS 2026. (*Equal contribution)

    arXiv

  2. Heterogeneous paper

    Is Depth Heterogeneity a Barrier to Model Merging?

    Nour Shaheen, Sarath Chandar, Boris Knyazev, Ekaterina Lobacheva.

    Accepted at the third workshop for Test-Time Updates at ICLR 2026.

    OpenReview

  3. Generalization paper

    Generalization Can Emerge in Tabular Foundation Models From a Single Table

    Junwei Ma, Nour Shaheen, Alex Labach, Amine Mhedhbi, Frank Hutter, Anthony L. Caterini, Valentin Thomas.

    Spotlight at the AI for Tabular Data workshop at EurIPS 2025.

    arXiv OpenReview

  4. SQL Routing paper

    Towards Optimizing SQL Generation via LLM Routing

    Mohammedhossein Malekpour, Nour Shaheen, Foutse Khomh, and Amine Mhedhbi.

    Accepted at NeurIPS 2024 Third Table Representation Learning Workshop (TRL @ NeurIPS).

    arXiv OpenReview

  5. C2F-CHART paper

    C2F-CHART: A Curriculum Learning Approach to Chart Classification

    Nour Shaheen, Tamer Elsharnouby, and Marwan Torki.

    Accepted at the 2024 International Conference on Pattern Recognition (ICPR).

    arXiv

Talks

  1. Understanding Out-of-Distribution Generalization in Tabular In-Context Learning

    • Prior-data Fitted Networks Reading Group, Mila · Montréal, Canada
    • Microsoft Research · Montréal, Canada
    • TRL Lab Seminar, CWI · Amsterdam, Netherlands
    • Samsung SAIT AI Lab (SAIL) · Montréal, Canada
    • MSc Thesis Defense, Polytechnique Montréal · Montréal, Canada

  2. Generalization Can Emerge in Tabular Foundation Models From a Single Table

    • Spotlight oral, AI for Tabular Data workshop, EurIPS 2025 · Copenhagen, Denmark

Education

MSc. in Computer Engineering

Aug 2024 – Jul 2026

Polytechnique Montréal · Quebec, Canada

cGPA: 4.0/4.0

  • Thesis: Understanding Out-of-Distribution Generalization in Tabular In-Context Learning.
  • Researcher in the Data & AI Systems Laboratory (DAIS) under the supervision of Prof. Amine Mhedhbi.
  • Researcher in the Chandar Research Lab and at Mila, co-supervised by Prof. Sarath Chandar.
  • Graduated with excellence and was nominated for the best thesis award.

BSc. in Computer and Communications Engineering

Sep 2019 – Jul 2024

Alexandria University · Alexandria, Egypt

cGPA: 3.99 / 4.0

  • Graduation Thesis: Developed a federated learning pipeline for cross-hospital digital pathology, implementing secure aggregation and client-side training on histopathology datasets. This was done under the supervision of Prof. Ayman Khalafallah.
  • Ranked 3rd in class with honors.

Research & Industry Experience

Visiting Researcher

September 2026 – Current

Centrum Wiskunde & Informatica (CWI) · Amsterdam, Netherlands

Research Master's Student

April 2025 – July 2026

Mila - Quebec AI Institute · Quebec, Canada

Computer Vision R&D Engineer

Sep 2023 – Jul 2024

Applied Innovation Center · Alexandria, Egypt

Machine Learning R&D Intern

Jul 2023 – Sep 2023

Microsoft · Cairo, Egypt

Computer Vision R&D Intern

May 2023 – Jun 2023

Mohammed Bin Zayed University of AI · Abu Dhabi, UAE

NLP & Data Science Intern

Mar 2023 – May 2023

ArabEasy LLC · Sharjah, UAE (Remote)

Computer Vision R&D Intern

Jul 2022 – May 2023

Applied Innovation Center · Alexandria, Egypt

TAships

INF3710: Files and Databases

Polytechnique Montréal

Description: Introduction to files and databases: needs analysis via the entity–relationship model; relational model and relational algebra; SQL DDL/DML and embedded SQL; concurrency control and transaction management; relational schema design (functional dependencies and normal forms); storage models and file structures; indexing and hashing.

  • Fall 2024 TA for Prof. Amine Mhedhbi
  • Winter 2025 TA for Prof. Omar Abdul Wahab
  • Summer 2025 TA for Dre. Franjieh El Khoury
  • Winter 2026 TA for Dre. Franjieh El Khoury

Awards

Mila EDI Excellence Scholarship - Women in AI

Awarded the Mila EDI Excellence Scholarship – Women in AI, a competitive award recognizing academic excellence and supporting the advancement of women in artificial intelligence. The scholarship aims to foster diversity and inclusion in the AI ecosystem by supporting high-potential researchers from underrepresented groups.