Arash Ahmadian

Joined

May 2023

Names

Arash Ahmadian (Preferred)

Emails

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

****@cohere.com (Confirmed)

Personal Links

Career & Education History

Undergrad student

University of Toronto (utoronto.ca)

2019 – 2024

Research Scholar

Cohere (cohere.om)

2023 – 2023

Advisors, Relations & Conflicts

No relations added

Expertise

Language Modelling

2023 – Present

Reinforcement Learning

2023 – Present

Aligment

2023 – Present

Publications

SimMerge: Learning to Select Merge Operators from Similarity Signals
Oliver Bolton, Aakanksha, Arash Ahmadian, Sara Hooker, Marzieh Fadaee, Beyza Ermis
- TTU at ICLR 2026 (Main)
- Readers: Everyone
Programming by Backprop: An Instruction is Worth 100 Examples When Finetuning LLMs
Jonathan Cook, Silvia Sapora, Arash Ahmadian, Akbir Khan, Tim Rocktäschel, Jakob Nicolaus Foerster, Laura Ruis
- ICLR 2026 Poster
- Readers: Everyone
Aya Vision: Advancing the Frontier of Multilingual Multimodality
Saurabh Dash, Yiyang Nan, John Dang, Arash Ahmadian, Shivalika Singh, Madeline Smith, Bharat Venkitesh, Vladyslav Shmyhlo, Viraat Aryabumi, Walter Beller-Morales, Jeremy Pekmez, Jason Ozuzu, Pierre Harvey Richemond, Acyr Locatelli, Nicholas Frosst, Phil Blunsom, Aidan Gomez, Ivan Zhang, Marzieh Fadaee, Manoj Govindassamy et al. (5 additional authors not shown)
- Submitted to ICLR 2026
- Readers: Everyone
Aya Vision: Advancing the Frontier of Multilingual Multimodality
Saurabh Dash, Yiyang Nan, John Dang, Arash Ahmadian, Shivalika Singh, Madeline Smith, Bharat Venkitesh, Vladyslav Shmyhlo, Viraat Aryabumi, Walter Beller-Morales, Jeremy Pekmez, Jason Ozuzu, Pierre Harvey Richemond, Acyr Locatelli, Nicholas Frosst, Phil Blunsom, Aidan Gomez, Ivan Zhang, Marzieh Fadaee, Manoj Govindassamy et al. (5 additional authors not shown)
- Submitted to NeurIPS 2025
- Readers: Everyone
Calibrated Value-Aware Model Learning with Probabilistic Environment Models
Claas A Voelcker, Anastasiia Pedan, Arash Ahmadian, Romina Abachi, Igor Gilitschenski, Amir-massoud Farahmand
- ICML 2025 poster
- Readers: Everyone
Mix Data or Merge Models? Optimizing for Performance and Safety in Multilingual Contexts
Aakanksha, Arash Ahmadian, Seraphina Goldfarb-Tarrant, Beyza Ermis, Marzieh Fadaee, Sara Hooker
- SafeGenAi Poster
- Readers: Everyone
Self-Improving Robust Preference Optimization
Eugene Choi, Arash Ahmadian, Matthieu Geist, Olivier Pietquin, Mohammad Gheshlaghi Azar
- ICLR 2025 Poster
- Readers: Everyone
Robust Chain of Thoughts Preference Optimization
Eugene Choi, Arash Ahmadian, Olivier Pietquin, Matthieu Geist, Mohammad Gheshlaghi Azar
- EWRL17
- Readers: Everyone
$\lambda$-AC: Effective decision-aware reinforcement learning with latent models
Claas A Voelcker, Arash Ahmadian, Romina Abachi, Igor Gilitschenski, Amir-massoud Farahmand
- Submitted to ICLR 2024
- Readers: Everyone
Pushing Mixture of Experts to the Limit: Extremely Parameter Efficient MoE for Instruction Tuning
Ted Zadouri, Ahmet Üstün, Arash Ahmadian, Beyza Ermis, Acyr Locatelli, Sara Hooker
- ICLR 2024 poster
- Readers: Everyone

View all 13 publications

Co-Authors

View all 50 co-authors