Mohammad Havaei

Reseach scientist, Research, Google

Joined

April 2018

Names

Mohammad Havaei (Preferred)

Emails

****@gmail.com (Confirmed)

****@imagia.com (Confirmed)

****@google.com (Confirmed)

Personal Links

Homepage

Google Scholar

DBLP

Career & Education History

Reseach scientist

Research, Google (google.com)

2022 – Present

Research Scientist

Research, Imagia (imagia.com)

2017 – 2022

Advisors, Relations & Conflicts

Postdoc Advisor

Aaron Courville

2017 – 2018

PhD Advisor

Hugo Larochelle

2012 – 2017

PhD Advisor

Pierre-marc Jodoin

2012 – 2017

Expertise

Deep learning

Computer Vision

Meta-learning

Medical imaging

2012 – 2017

Publications

Position: Causality Is Key to Understand and Balance Multiple Goals in Trustworthy ML and Foundation Models
Ruta Binkyte, Ivaxi Sheth, Zhijing Jin, Mohammad Havaei, Bernhard Schölkopf, Mario Fritz
- Submitted to ICML 2025 Position Paper Track
- Readers: Everyone
PRISM: High-Resolution & Precise Counterfactual Medical Image Generation using Language-guided Stable Diffusion
Amar Kumar, Anita Kriz, Mohammad Havaei, Tal Arbel
- MIDL 2025 Oral
- Readers: Everyone
What Secrets Do Your Manifolds Hold? Understanding the Local Geometry of Generative Models
Ahmed Imtiaz Humayun, Ibtihel Amara, Cristina Nader Vasconcelos, Deepak Ramachandran, Candice Schumann, Junfeng He, Katherine A Heller, Golnoosh Farnadi, Negar Rostamzadeh, Mohammad Havaei
- ICLR 2025 Poster
- Readers: Everyone
On The Local Geometry of Deep Generative Manifolds
Ahmed Imtiaz Humayun, Ibtihel Amara, Candice Schumann, Golnoosh Farnadi, Negar Rostamzadeh, Mohammad Havaei
- ICML 2024 Workshop GRaM
- Readers: Everyone
Position: Cracking the Code of Cascading Disparity Towards Marginalized Communities
Golnoosh Farnadi, Mohammad Havaei, Negar Rostamzadeh
- ICML 2024 Poster
- Readers: Everyone
DeCoDEx: Confounder Detector Guidance for Improved Diffusion-based Counterfactual Explanations
Nima Fathi, Amar Kumar, Brennan Nichyporuk, Mohammad Havaei, Tal Arbel
- MIDL 2024 Oral
- Readers: Everyone
Learning from uncertain concepts via test time interventions
Ivaxi Sheth, Aamer Abdul Rahman, Laya Rafiee Sevyeri, Mohammad Havaei, Samira Ebrahimi Kahou
- Published: 21 Nov 2022, Last Modified: 05 May 2023
- TSRML2022
- Readers: Everyone
Pitfalls of conditional computation for multi-modal learning
Ivaxi Sheth, Mohammad Havaei, Samira Ebrahimi Kahou
- Published: 06 Dec 2022, Last Modified: 05 May 2023
- ICBINB poster
- Readers: Everyone
FL Games: A Federated Learning Framework for Distribution Shifts
Sharut Gupta, Kartik Ahuja, Mohammad Havaei, Niladri Chatterjee, Yoshua Bengio
- Published: 21 Oct 2022, Last Modified: 15 Jan 2026
- FL-NeurIPS 2022 Oral
- Readers: Everyone
Shift and Scale is Detrimental To Few-Shot Transfer
Moslem Yazdanpanah, Aamer Abdul Rahman, Christian Desrosiers, Mohammad Havaei, Eugene Belilovsky, Samira Ebrahimi Kahou
- Published: 02 Dec 2021, Last Modified: 05 May 2023
- NeurIPS 2021 Workshop DistShift Poster
- Readers: Everyone

View all 33 publications

Co-Authors

View all 66 co-authors