Mohammad Mahdi Derakhshani
Computer Vision | Machine Learning
Hi! I'm Mohammad, a Ph.D. student of VIS lab at
the
University of Amsterdam working with Cees
Snoek and Yuki
Asano. My
Ph.D.
thesis is Efficient Adaptation of Large-scale Vision and Language Models.
Specifically, my current focus is on the implementation of prompting and chain of thoughts for
multi-modal reasoning.
In summer 2022, I was also a ML/CV intern at Samsung AI Center (SAIC) in Cambridge working with Brais Martinez and
Georgios
Tzimiropoulos
doing research on Prompting of large-scale language-image models and
Federated Learning.
Previously I was a master student at the University of Tehran working with Babak Nadjar Araabi and Mohammad Amin
Sadeghi. I
did my master at machine learning and computational modeling lab working on object detection and
image compression. During my master degree, I also did research on object detection with Mohammad Rastegari at
Allen AI Institute.
I am a member of ELLIS society, and
I
have served as reviewer for ICCV'21, ICML'22, CVPR'23, ICLR'23, and TPAMI.
