Amil Dravid
Scholar

Amil Dravid

Google Scholar ID: YZ8Y-sUAAAAJ
UC Berkeley
Deep LearningMachine LearningArtificial IntelligenceComputer Vision
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
346
 
H-index
7
 
i10-index
7
 
Publications
13
 
Co-authors
6
list available
Contact
TwitterOpen ↗GitHubOpen ↗LinkedInOpen ↗
Publications
1 items
Vision Transformers Don't Need Trained Registers
2025
Cited
0
Resume (English only)
Academic Achievements
  • Co-first authored paper 'Vision Transformers Don't Need Trained Registers' accepted as a Spotlight (top 3%) at NeurIPS 2025
  • Published 'Interpreting the Weight Space of Customized Diffusion Models' at NeurIPS 2024
  • Published 'Idempotent Generative Network' at ICLR 2024
  • Co-first authored 'Rosetta Neurons: Mining the Common Units in a Model Zoo' at ICCV 2023
  • Co-organized the 'Mechanistic Interpretability for Vision Workshop' at CVPR in June 2025
Co-authors
6 total
Aggelos K Katsaggelos
Aggelos K Katsaggelos
Joseph Cummings Professor of ECE (Courtesy CS and Radiology), Northwestern University
Yossi Gandelsman
Yossi Gandelsman
Reve.art
Alexei A. Efros
Alexei A. Efros
Dept. of Electrical Engineering and Computer Sciences, UC Berkeley
Assaf Shocher
Assaf Shocher
Assistant Professor at Technion
Jennifer J. Sun
Jennifer J. Sun
Assistant professor at Cornell CS
Pietro Perona
Pietro Perona
California Institute of Technology