Scholar
Valentino Maiorca
Google Scholar ID: 2VUUfFEAAAAJ
Apple MLR intern. ELLIS Ph.D. Student. Sapienza University of Rome & ISTA
Representation Learning
Representation Alignment
Mechanistic Interpretability
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
541
H-index
8
i10-index
8
Publications
20
Co-authors
13
list available
Publications
10 items
Emergent Structure in the Marginal Attention Space of Language Models
2026
Cited
0
$\lambda$-JEPA Spectral Anti-Collapse Regularization for Self-Supervised Learning
2026
Cited
0
LocUS: Head Selection and Subspace Projection for Targeted Activation Steering
2026
Cited
0
Assessing Sample Quality in Conditional Generation under Compositional Shift
2026
Cited
0
HyperTransport: Amortized Conditioning of T2I Generative Models
2026
Cited
0
Head Pursuit: Probing Attention Specialization in Multimodal Transformers
2025
Cited
0
Mapping representations in Reinforcement Learning via Semantic Alignment for Zero-Shot Stitching
2025
Cited
0
ResiDual Transformer Alignment with Spectral Decomposition
arXiv.org · 2024
Cited
1
Load more
Co-authors
12 total
Emanuele Rodolà
Professor of Computer Science, Sapienza University of Rome
Luca Moschella
Apple
Marco Fumero
PostDoctoral Researcher, Institute of Science and Technology Austria (ISTA)
Francesco Locatello
Assistant Professor, ISTA
Riccardo Marin
Technical University of Munich
Roberto Navigli
Professor, Sapienza University of Rome
Fabrizio Silvestri
Sapienza, University of Rome
Gabriele Tolomei
Associate Professor of Computer Science at Sapienza University of Rome
