Showing cs.LGShow all
2 papers · 1 filter
cs.LG2025
Emergent World Representations in OpenVLA
Marco Molinari, Leonardo Nevali, Saharsha Navani +1
Vision Language Action models (VLAs) trained with policy-based reinforcement learning (RL) encode complex behaviors without explicitly modeling environmental dynamics. However, it…
cs.LG2025
Fixed Point Explainability
Emanuele La Malfa, Jon Vadillo, Marco Molinari +1
This paper introduces a formal notion of fixed point explanations, inspired by the "why regress" principle, to assess, through recursive applications, the stability of the interpla…