Meir Yossef Levi

I received my BSc and MSc from the Technion Institute of Technology in Haifa, Israel. I am at the final stages of my PHd under the guidance of Prof. Guy Gilboa from the Electrical & Computer Engineering faculty.

My research focuses on gaining a deep understanding of the inner mechanisms of machine learning systems, with a particular emphasis on vision-language models. I study the geometry and probabilistic structure of their latent spaces. Previously, my work centered on 3D computer vision, especially robust point cloud classification.

Email    Google Scholar    LinkedIn    GitHub

Meir Yossef Levi

News

[July 2025] A talk on CLIP latent space in UBC, NLP Group (Vered Shwartz's lab)!
[July 2025] A talk on CLIP latent space in Caltech, Vision Lab (Pietro perona's lab)!
[July 2025] Presenting two papers in ICML 25 in Vancouver!

Publications

Whitened CLIP as a Likelihood Surrogate of Images and Captions
Roy Betser, Meir Yossef Levi, Guy Gilboa
ICML, 2025
paper / code / video
The double-ellipsoid geometry of clip
Meir Yossef Levi, Guy Gilboa
ICML, 2025
paper / code / video / project page
Fast and simple explainability for point cloud networks
Meir Yossef Levi, Guy Gilboa
arXiv, 2024
paper
Robustifying point cloud networks by refocusing
Meir Yossef Levi, Guy Gilboa
3DV, 2025
paper / code
EPiC: Ensemble of Partial Point Clouds for Robust Classification
Meir Yossef Levi, Guy Gilboa
ICCV, 2023
paper / code / video / project page