Scholar
Jonas Ngnawé
Google Scholar ID: KwAxSFsAAAAJ
Université Laval, Mila-Quebec AI Institute, Stanford University
Machine Learning
Deep Learning
Trustworthy AI
Adversarial Robustness
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
13
H-index
3
i10-index
0
Publications
10
Co-authors
0
Publications
4 items
Mind the Spike: Mechanisms and Brittleness of Visual Massive Activations in Large Vision-Language Models
2026
Cited
0
A Stochastic--Geometric Theory of Scaling Laws in Grokking
2026
Cited
0
Robust Fine-Tuning from Non-Robust Pretrained Models: Mitigating Suboptimal Transfer With Adversarial Scheduling
2025
Cited
0
A Guide to Robust Generalization: The Impact of Architecture, Pre-training, and Optimization Strategy
2025
Cited
0
