collaborators

6 papers

cs.AI2026

Subliminal Clocks: Latent Time Modelling in Diffusion Language Models

Maximo Rulli, Maximo Eduardo Rulli, Thomas Vaitses Fontanari +11

Diffusion Language Models (DLMs) have recently emerged as a promising alternative to autoregressive models. Unlike standard diffusion-based approaches, DLMs are not explicitly cond…

cs.LG2026

Language Models are Injective and Hence Invertible

Giorgos Nikolaou, Tommaso Mencattini, Donato Crisostomi +3

Transformer components such as non-linear activations and normalization are inherently non-injective, suggesting that different inputs could map to the same output and prevent exac…

cs.CV2025

Escaping Plato's Cave: Towards the Alignment of 3D and Text Latent Spaces

Souhail Hadgi, Luca Moschella, Andrea Santilli +5

Recent works have shown that, when trained at scale, uni-modal 2D vision and text encoders converge to learned features that share remarkable structural properties, despite arising…

cs.LG2025

Mergenetic: a Simple Evolutionary Model Merging Library

Adrian Robert Minut, Tommaso Mencattini, Andrea Santilli +2

Model merging allows combining the capabilities of existing models into a new one - post hoc, without additional training. This has made it increasingly popular thanks to its low c…

cs.NE2025

MERGE: Efficient Evolutionary Merging on Consumer-grade GPUs

Tommaso Mencattini, Adrian Robert Minut, Donato Crisostomi +2

Evolutionary model merging enables the creation of high-performing multi-task models but remains computationally prohibitive for consumer hardware. We introduce MERGE, an effic…

cs.CR2025

Preserving Privacy in Large Language Models: A Survey on Current Threats and Solutions

Michele Miranda, Elena Sofia Ruzzetti, Andrea Santilli +3

Large Language Models (LLMs) represent a significant advancement in artificial intelligence, finding applications across various domains. However, their reliance on massive interne…