Babak Ehteshami Bejnordi

Researcher, Qualcomm AI Research, Qualcomm Inc, QualComm, Qualcomm AI Research, Qualcomm Inc, QualComm

Joined

April 2018

Names

Emails

****@gmail.com (Confirmed)

****@qti.qualcomm.com (Confirmed)

Personal Links

Homepage

Google Scholar

DBLP

Career & Education History

Researcher

Qualcomm AI Research, Qualcomm Inc, QualComm, Qualcomm AI Research, Qualcomm Inc, QualComm (qti.qualcomm.com)

2018 – Present

Advisors, Relations & Conflicts

No relations added

Expertise

Computer vision

Present

Machine learning

Present

Artificial Intelligence

Present

Mixture of Experts

Present

Conditional computation

2018 – Present

dynamic neural networks

2018 – Present

efficient training and inference

2018 – Present

Publications

DIRICHLET-PRIOR SHAPING: GUIDING EXPERT SPECIALIZATION IN UPCYCLED MOES
Leyla Mirvakhabova, Babak Ehteshami Bejnordi, Gaurav Kumar, Hanxue Liang, Wanru Zhao, Paul N. Whatmough
- SPOT
- Readers: Everyone
KaVa: Latent Reasoning via Compressed KV-Cache Distillation
Anna Kuzina, Maciej Pióro, Babak Ehteshami Bejnordi
- ICLR 2026 Poster
- Readers: Everyone
Dirichlet-Prior Shaping: Guiding Expert Specialization in Upcycled MoEs
Leyla Mirvakhabova, Babak Ehteshami Bejnordi, Gaurav Kumar, Hanxue Liang, Wanru Zhao, Paul N. Whatmough
- Submitted to ICLR 2026
- Readers: Everyone
Mixture of Cache-Conditional Experts for Efficient Mobile Device Inference
Andrii Skliar, Ties van Rozendaal, Romain Lepert, Todor Boinovski, Mart Van Baalen, Markus Nagel, Paul N. Whatmough, Babak Ehteshami Bejnordi
- Accepted by TMLR
- Readers: Everyone
Think Big, Generate Quick: LLM-to-SLM for Fast Autoregressive Decoding
Benjamin Bergner, Andrii Skliar, Amelie Royer, Tijmen Blankevoort, Yuki M Asano, Babak Ehteshami Bejnordi
- ES-FoMo-II 2024 Poster
- Readers: Everyone
$\textit{Read-ME}$: Refactorizing LLMs as Router-Decoupled Mixture of Experts with System Co-Design
Ruisi Cai, Yeonju Ro, Geon-Woo Kim, Peihao Wang, Babak Ehteshami Bejnordi, Aditya Akella, Zhangyang Wang
- NeurIPS 2024 poster
- Readers: Everyone
GatedMTL: Learning to Share, Specialize, and Prune Representations for Multi-task Learning
Babak Ehteshami Bejnordi, Gaurav Kumar, Amelie Royer, Christos Louizos, Tijmen Blankevoort, Mohsen Ghafoorian
- Submitted to ICLR 2024
- Readers: Everyone
Scalarization for Multi-Task and Multi-Domain Learning at Scale
Amelie Royer, Tijmen Blankevoort, Babak Ehteshami Bejnordi
- NeurIPS 2023 poster
- Readers: Everyone
Computational Pathology: A Survey Review and The Way Forward
Mahdi S. Hosseini, Babak Ehteshami Bejnordi, Vincent Quoc-Huy Trinh, Danial Hasan, Xingwen Li, Taehyo Kim, Haochen Zhang, Theodore Wu, Kajanan Chinniah, Sina Maghsoudlou, Ryan Zhang, Stephen Yang, Jiadai Zhu, Lyndon Chan, Samir Khaki, Andrei Buin, Fatemeh Chaji, Ala Salehi, Alejandra Zambrano Luna, Bich Ngoc Nguyen et al. (2 additional authors not shown)
- 2023 (modified: 21 Apr 2023)
- CoRR 2023
- Readers: Everyone
Revisiting Single-gated Mixtures of Experts
Amelie Royer, Ilia Karmanov, Andrii Skliar, Babak Ehteshami Bejnordi, Tijmen Blankevoort
- 2023 (modified: 21 Apr 2023)
- CoRR 2023
- Readers: Everyone

View all 43 publications

Co-Authors

View all 163 co-authors