Scholar
Meir Yossef Levi
Google Scholar ID: 7k8ZP6UAAAAJ
PhD student, Electrical Engineering, Technion - Israel Institute of Technolgy
point-clouds classification
representation learning
vision language models
latent space
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
27
H-index
3
i10-index
1
Publications
6
Co-authors
3
list available
Contact
Email
yossilevii100@gmail.com
CV
Open ↗
GitHub
Open ↗
LinkedIn
Open ↗
Publications
7 items
The Universal Normal Embedding
2026
Cited
0
Training-free Detection of Generated Videos via Spatial-Temporal Likelihoods
2026
Cited
0
Make it SING: Analyzing Semantic Invariants in Classifiers
2026
Cited
0
SCoCCA: Multi-modal Sparse Concept Decomposition via Canonical Correlation Analysis
2026
Cited
0
InfoNCE Induces Gaussian Distribution
2026
Cited
0
Whitened CLIP as a Likelihood Surrogate of Images and Captions
2025
Cited
0
The Double-Ellipsoid Geometry of CLIP
arXiv.org · 2024
Cited
1
Resume (English only)
Academic Achievements
Published two papers at ICML 2025: 'Whitened CLIP as a Likelihood Surrogate of Images and Captions' and 'The double-ellipsoid geometry of clip'.
Published 'Fast and simple explainability for point cloud networks' on arXiv in 2024.
Published 'Robustifying point cloud networks by refocusing' at 3DV 2025.
Published 'EPiC: Ensemble of Partial Point Clouds for Robust Classification' at ICCV 2023.
Gave talks on CLIP latent space at UBC NLP Group (Vered Shwartz's lab) and Caltech Vision Lab (Pietro Perona's lab) in July 2025.
Wrote a Medium blog post on the geometry of CLIP latent space in October 2025.
Co-authors
3 total
Guy Gilboa
Electrical Engineering, Technion - Israel Institute of Technolgy
Tomer Michaeli
Associate Professor, ECE, Technion; Visiting Researcher, Google DeepMind
Roy Betser
Ph.D. candidate at the Technion – Israel Institute of Technology
×
Welcome back
Sign in to Agora
Welcome back! Please sign in to continue.
Email address
Password
Forgot password?
Continue
Do not have an account?
Sign up