Mandana Samiei

PhD student, Computer Science, McGill University

Joined

February 2021

Names

Mandana Samiei (Preferred)

Emails

****@mail.mcgill.ca (Confirmed)

****@gmail.com (Confirmed)

****@mcgill.ca (Confirmed)

****@mila.quebec (Confirmed)

Personal Links

Homepage

Career & Education History

PhD student

Computer Science, McGill University (mcgill.ca)

2021 – 2027

Advisors, Relations & Conflicts

PhD Advisor

Doina Precup

2020 – Present

PhD Advisor

Blake A. Richards

2020 – Present

Expertise

Reinforcement Learning

2021 – Present

Continual learning

Meta-learning

2021 – Present

Biological-inspired learning

Neuro AI

2021 – Present

Publications

AIF-GEN: Open-Source Platform and Synthetic Dataset Suite for Reinforcement Learning on Large Language Models
Shahrad Mohammadzadeh, Jacob Chmura, Ivan Anokhin, Jacob-Junqi Tian, Mandana Samiei, Taz Scott-Talib, Irina Rish, Doina Precup, Reihaneh Rabbany, Nishanth Anand
- LLA 2026 Poster
- Readers: Everyone
Local Inconsistency Resolution: The Interplay between Attention and Control in Probabilistic Models
Oliver Ethan Richardson, Mandana Samiei, Mehran Shakerinava, Joseph D Viviano, Abdessamad El Kabid, Ali Parviz, Yoshua Bengio
- AISTATS 2026 Spotlight
- Readers: Everyone
NeuMoSync: End‑to‑End Neuromodulatory Control for Plasticity and Adaptability in Continual Learning
Seyed Roozbeh Razavi Rohani, Khashayar Khajavi, Wesley Chung, Mandana Samiei, Mo Chen
- Submitted to ICLR 2026
- Readers: Everyone
AIF-GEN: Open-Source Platform and Synthetic Dataset Suite for Reinforcement Learning on Large Language Models
Jacob Chmura, Shahrad Mohammadzadeh, Ivan Anokhin, Jacob-Junqi Tian, Mandana Samiei, Taz Scott-Talib, Irina Rish, Doina Precup, Reihaneh Rabbany, Nishanth Anand
- CODEML@ICML25
- Readers: Everyone
Language Agents Mirror Human Causal Reasoning Biases. How Can We Help Them Think Like Scientists?
Anthony GX-Chen, Dongyan Lin, Mandana Samiei, Doina Precup, Blake Aaron Richards, Rob Fergus, Kenneth Marino
- COLM 2025
- Readers: Everyone
Is multitask learning all you need in continual learning?
Giulia Lanzillotta, Mandana Samiei, Claire Vernade, Razvan Pascanu
- Submitted to ICLR 2025
- Readers: Everyone
Testing causal hypotheses through Hierarchical Reinforcement Learning
Anthony GX-Chen, Dongyan Lin, Mandana Samiei
- NeurIPS 2024 Workshop IMOL asTinyPaperPoster
- Readers: Everyone
The TCGA Meta-Dataset Clinical Benchmark
Mandana Samiei, Tobias Würfl, Tristan Deleu, Martin Weiss, Francis Dutil, Thomas Fevens, Sebastien Lemieux, Joseph Paul Cohen
- 24 May 2022
- OpenReview Archive Direct Upload
- Readers: Everyone
Torchmeta: A Meta-Learning library for PyTorch
Mandana Samiei, Tristan Deleu, Tobias Würfl, Joseph Paul Cohen, Yoshua Bengio
- 24 May 2022
- OpenReview Archive Direct Upload
- Readers: Everyone

Co-Authors

View all 34 co-authors