Amil Dravid Profile

Amil Dravid

PhD @ Berkeley AI Research
amil_dravid [at] berkeley.edu

About Me

Hi! I am a PhD student at Berkeley AI Research, advised by Alexei A. Efros. I am interested in understanding emergent phenomena in deep learning. Lately, I have been thinking about linearity in weight space and mode connectivity, learning dynamics, universality in representations, and the role of data. My goal is to leverage these insights to guide the design of better algorithms and models. My research is supported by the DOE Computational Science Graduate Fellowship.

Previously, I graduated from Northwestern in 2023 with a BS in Computer Science. During my undergrad, I had the pleasure of working with many wonderful mentors: Aggelos Katsaggelos, Pietro Perona, Jennifer J. Sun, Vibhav Vineet, and Neel Joshi.

Selected Publications


(See my Google Scholar for a full list)

Vision Transformers Don't Need Trained Registers
Nick Jiang*, Amil Dravid*, Alexei A. Efros, Yossi Gandelsman
Preprint 2025
Interpreting the Weight Space of Customized Diffusion Models
Amil Dravid*, Yossi Gandelsman*, Kuan-Chieh Wang, Rameen Abdal, Gordon Wetzstein, Alexei A. Efros, Kfir Aberman
NeurIPS 2024
Idempotent Generative Network
Assaf Shocher, Amil Dravid, Yossi Gandelsman, Inbar Mosseri, Miki Rubinstein, Alexei A. Efros
ICLR 2024
Rosetta Neurons: Mining the Common Units in a Model Zoo
Amil Dravid*, Yossi Gandelsman*, Alexei A. Efros, Assaf Shocher
ICCV 2023