Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
Sensory-Motor Control with Large Language Models via Iterative Policy Refinement
Jônata Tyska Carvalho, Stefano Nolfi
We propose a method that enables large language models (LLMs) to control embodied agents through the generation of control policies that directly map continuous observation vectors…
cs.AI2026
Alignment among Language, Vision and Action Representations
Nicola Milano, Stefano Nolfi
A fundamental question in cognitive science and AI concerns whether different learning modalities: language, vision, and action, give rise to distinct or shared internal representa…