activity
20222026
most citedHeat Death of Generative Models in Closed-Loop Learning

2 citations · 3 across the 4 of their papers we have counts for

collaborators
Showing cs.AIShow all

1 paper · 1 filter

cs.AI2024

Meanings and Feelings of Large Language Models: Observability of Latent States in Generative AI

Tian Yu Liu, Stefano Soatto, Matteo Marchi +2

We tackle the question of whether Large Language Models (LLMs), viewed as dynamical systems with state evolving in the embedding space of symbolic tokens, are observable. That is,…