Dvir Samuel  

 



  ![](/sites/default/files/person/Dvir_Samuel.png)

  

 Dvir Samuel joined NVIDIA Research as a Research Scientist in 2026. His main fields of interest are machine learning and generative modeling. In particular, he studies diffusion- and flow-matching methods for image and video generation and editing, with an emphasis on personalization, controllability, and learning under long-tailed data regimes.

Dvir completed his Ph.D. at Bar-Ilan University under the supervision of Prof. Gal Chechik. His research spans long-tail and few-shot learning, as well as modern generative approaches for visual content creation and manipulation.

Personal website: <https://dvirsamuel.github.io/>



   Research Area(s)

[Computer Graphics](/research-area/computer-graphics)

[Computer Vision](/research-area/computer-vision)

[Generative AI](/research-area/generative-ai)

 

 

  

 Main Field of Interest

[Computer Vision](/research-area/computer-vision)

 

  

 Google Scholar

[https://scholar.google.com/citations?user=\_CWxQ1gAAAAJ&amp;hl=en](https://scholar.google.com/citations?user=_CWxQ1gAAAAJ&hl=en)