Research

← Back to home

My research explores how neural systems, biological or artificial, learn to distill experience into meaning — learning the abstractions that guide reasoning and decision.

Selected Publications

* indicates co-first author

Reasoning aligns language models to human cognition

Gonçalo Guiomar*, Elia Torre*, Pehuen Moure, Victoria Shavina, Mario Giulianelli, Shih-Chii Liu, Valerio Mante

Under Review ICML 2026 CTB Workshop (Oral) Learn more

Mechanistic Interpretability of RNNs emulating Hidden Markov Models

Elia Torre, Michele Viscione, Lucas Pompe, Benjamin F Grewe, Valerio Mante

NeurIPS 2025 Learn more

Open Projects

Diffusion RNNs: modeling naturalistic behaviors with noise

Elia Torre, Liyuan Li, Gonçalo Guiomar, Lucas Pompe, Renate Krause, Valerio Mante

Work in Progress COSYNE 2026 Learn more

Probabilistic Reasoning in Humans, Language Models and Recurrent Networks

Elia Torre, Gonçalo Guiomar and Valerio Mante

Work in Progress Learn more