↓ Skip to main content

NLP

Perseus: Faster FHE Transformer Inference via Complex-Packing and Sparse Bootstraps
Alessandro Zirilli , 

Davide Marincione

, 

Evgenios M. Kornaropoulos

, 

Giuseppe Ateniese

, 

Emanuele Rodolà

·1 min
FHE Cryptography Privacy NLP Efficiency
HEAT: Faster Fully Homomorphic Inference via Approximations-Weights Co-Adaptation
Alessandro Zirilli , 

Davide Marincione

, 

Evgenios M. Kornaropoulos

, 

Giuseppe Ateniese

, 

Emanuele Rodolà

·2 mins
🏆NeurIPS2026 Workshops FHE Cryptography Privacy NLP Efficiency
MASS: MoErging through Adaptive Subspace Selection

Donato Crisostomi

,  Alessandro Zirilli , 

Antonio Andrea Gargiulo

, 

Maria Sofia Bucarelli

, 

Simone Scardapane

, 

Fabrizio Silvestri

, 

Iacopo Masi

, 

Emanuele Rodolà

·1 min
🏆ICLR2026 MoErging Merging Vision NLP Interpretation