Scholar
Florent Krzakala
Google Scholar ID: 3jDeUlMAAAAJ
École polytechnique fédérale de Lausanne
Statistical Mechanics
Statistics
Machine Learning
Information theory
Spin Glasses
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
10,574
H-index
56
i10-index
153
Publications
20
Co-authors
165
list available
Contact
Email
florent.krzakala@epfl.ch
CV
Open ↗
Twitter
Open ↗
GitHub
Open ↗
Publications
27 items
Symmetry-Aware Feature Learning: A Polynomial Separation for Multi-Index Models
2026
Cited
0
High-Dimensional Learning Dynamics of Attention-Indexed Models
2026
Cited
0
How Width and Data Shape Generalization Scaling Laws in Quadratic Neural Networks
2026
Cited
0
Scaling Laws from Sequential Feature Recovery: A Solvable Hierarchical Model
2026
Cited
0
Deep Learning as Neural Low-Degree Filtering: A Spectral Theory of Hierarchical Feature Learning
2026
Cited
0
A Noise Sensitivity Exponent Controls Large Statistical-to-Computational Gaps in Single- and Multi-Index Models
2026
Cited
0
ColBERT-Zero: To Pre-train Or Not To Pre-train ColBERT models
2026
Cited
0
Deep Learning of Compositional Targets with Hierarchical Spectral Methods
2026
Cited
0
Load more
Co-authors
15 total
Lenka Zdeborová
EPFL, Switzerland
Bruno Loureiro
École Normale Supérieure & CNRS
Marc Mezard
Bocconi University Milano
Sylvain Gigan
Professor, Sorbonne Université / Lab. Kastler-Brossel / CNRS / Ecole Normale Supérieure
Jean Barbier
Associate Professor, International Center for Theoretical Physics
Nicolas Macris
Ecole Polytechnique Federale Lausanne
Hugo Cui
Postdoctoral fellow, Harvard CMSA
Sebastian Goldt
International School of Advanced Studies (SISSA), Trieste, Italy
