Scholar
David Dinkevich
Google Scholar ID: Y-_RbNAAAAAJ
Hebrew University of Jerusalem
Citations & Impact
Citations
0
H-index
0
i10-index
0
Publications
1
Co-authors
4
list available
Resume (English only)
Academic Achievements
- Selected publication: 'Story2Board: A Training-Free Approach for Expressive Storyboard Generation', authors include David Dinkevich, Matan Levy, Omri Avrahami, and 2 more, preprint available on arXiv.
Research Experience
- Current work focuses on post-training methods that make diffusion-based video models behave reliably for real users: less prompt fragile, more controllable, and consistent across shots.
Education
- MSc thesis: 'Story2Board: A Training-Free Approach for Expressive Storyboard Generation', exploring adapting attention mechanisms in transformer-based image models to improve character consistency across frames.
Background
- Machine Learning researcher and PhD student at the Hebrew University of Jerusalem, working under the supervision of Prof. Dani Lischinski. Research focuses on generative models for images and video.
Miscellany
- Resume is available here.
