Mohammad Mahdi Derakhshani
Scholar

Mohammad Mahdi Derakhshani

Google Scholar ID: n7GnOJoAAAAJ
University of Amsterdam, Video & Image Sense Lab
Vision and Language ModelsGenerative Models
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
425
 
H-index
8
 
i10-index
8
 
Publications
16
 
Co-authors
9
list available
Contact
No contact links provided.
Publications
7 items
GAP3D: Generative Alignment of VLM Latents to Patch-Level Embeddings for 3D Generation
2026
Cited
0
Private PoEtry: Private In-Context Learning via Product of Experts
2026
Cited
0
Purrception: Variational Flow Matching for Vector-Quantized Image Generation
2025
Cited
0
NeoBabel: A Multilingual Open Tower for Visual Generation
2025
Cited
0
Continual Hyperbolic Learning of Instances and Classes
2025
Cited
0
TWIST&SCOUT: Grounding Multimodal LLM-Experts by Forget-Free Tuning
2024
Cited
0
TULIP: Token-length Upgraded CLIP
arXiv.org · 2024
Cited
2
Resume (English only)
Co-authors
9 total
Cees G. M. Snoek
Cees G. M. Snoek
Professor of Computer Science, University of Amsterdam
Co-author 2
Co-author 2
Xiantong Zhen
Xiantong Zhen
United Imaging
Georgios (Yorgos) Tzimiropoulos
Georgios (Yorgos) Tzimiropoulos
Samsung AI Center, Cambridge | Queen Mary University of London
Brais Martinez
Brais Martinez
Samsung AI Centre
Mohammad Amin Sadeghi
Mohammad Amin Sadeghi
Qatar Computing Research Institute
Ling Shao, Fellow of IEEE/IAPR
Ling Shao, Fellow of IEEE/IAPR
Terminus; Founder of IIAI/MBZUAI
Yuki M. Asano
Yuki M. Asano
Full Professor, Head of FunAI Lab, University of Technology Nuremberg