Saba Ahmadi

Researcher, Noah's Ark Lab, Huawei Technologies Ltd.

Joined

June 2023

Names

Saba Ahmadi (Preferred)

Emails

****@mila.quebec (Confirmed)

****@gmail.com (Confirmed)

Personal Links

Homepage

Google Scholar

ACL Anthology

Career & Education History

Researcher

Noah's Ark Lab, Huawei Technologies Ltd. (h-partners.com)

2025 – Present

Researcher

Mila - Quebec Artificial Intelligence Institute (mila.quebec)

2024 – 2025

MS student

Université de Montréal (umontreal.ca)

2021 – 2023

Undergrad student

Isfahan University of Technology (iut.ac.ir)

2014 – 2019

Advisors, Relations & Conflicts

Coworker

Aishwarya Agrawal

2023 – Present

Master's Advisor

Aishwarya Agrawal

2021 – 2023

Expertise

multimodal artificial intelligence

vision and language

Present

Publications

The Promise of RL for Autoregressive Image Editing
Saba Ahmadi, Rabiul Awal, Ankur Sikarwar, Amirhossein Kazemnejad, Ge Ya Luo, Juan A. Rodriguez, Sai Rajeswar, Siva Reddy, Christopher Pal, Benno Krojer, Aishwarya Agrawal
- NeurIPS 2025 poster
- Readers: Everyone
VisMin: Visual Minimal-Change Understanding
Rabiul Awal, Saba Ahmadi, Le Zhang, Aishwarya Agrawal
- NeurIPS 2024
- Readers: Everyone
VisMin: Visual Minimal-Change Understanding
Rabiul Awal, Saba Ahmadi, Le Zhang, Aishwarya Agrawal
- NeurIPS 2024 poster
- Readers: Everyone
MAPL: Parameter-Efficient Adaptation of Unimodal Pre-Trained Models for Vision-Language Few-Shot Prompting
Oscar Mañas, Pau Rodriguez, Saba Ahmadi, Aida Nematzadeh, Yash Goyal, Aishwarya Agrawal
- 01 Nov 2023
- OpenReview Archive Direct Upload
- Readers: Everyone
MAPL: Parameter-Efficient Adaptation of Unimodal Pre-Trained Models for Vision-Language Few-Shot Prompting
Oscar Mañas, Pau Rodríguez López, Saba Ahmadi, Aida Nematzadeh, Yash Goyal, Aishwarya Agrawal
- Published: 01 Jan 2023, Last Modified: 29 Jun 2023
- EACL 2023
- Readers: Everyone
An Examination of the Robustness of Reference-Free Image Captioning Evaluation Metrics
Saba Ahmadi, Aishwarya Agrawal
- Published: 01 Jan 2023, Last Modified: 29 Jun 2023
- CoRR 2023
- Readers: Everyone
MAPL: Parameter-Efficient Adaptation of Unimodal Pre-Trained Models for Vision-Language Few-Shot Prompting
Oscar Mañas, Pau Rodríguez, Saba Ahmadi, Aida Nematzadeh, Yash Goyal, Aishwarya Agrawal
- 2022 (modified: 24 Apr 2023)
- CoRR 2022
- Readers: Everyone

Saba Ahmadi

Names

Emails

Personal Links

Career & Education History

Advisors, Relations & Conflicts

Expertise

Publications

The Promise of RL for Autoregressive Image Editing

VisMin: Visual Minimal-Change Understanding

VisMin: Visual Minimal-Change Understanding

MAPL: Parameter-Efficient Adaptation of Unimodal Pre-Trained Models for Vision-Language Few-Shot Prompting

MAPL: Parameter-Efficient Adaptation of Unimodal Pre-Trained Models for Vision-Language Few-Shot Prompting

An Examination of the Robustness of Reference-Free Image Captioning Evaluation Metrics

MAPL: Parameter-Efficient Adaptation of Unimodal Pre-Trained Models for Vision-Language Few-Shot Prompting

Co-Authors