Showing cs.ROShow all
2 papers · 1 filter
cs.RO2026
Decoupled Early Exits for Task-Dependent Compute Allocation in Flow-Matching VLAs
Riccardo Andrea Izzo, Rimvydas Rubavicius, Gianluca Bardaro +3
Flow-matching Vision-Language-Action (VLA) models have emerged as a potential solution for generalist robot control, designed by combining a pretrained Vision-Language Model (VLM)…
cs.RO2024
SECURE: Semantics-aware Embodied Conversation under Unawareness for Lifelong Robot Learning
Rimvydas Rubavicius, Peter David Fagan, Alex Lascarides +1
This paper addresses a challenging interactive task learning scenario we call rearrangement under unawareness: an agent must manipulate a rigid-body environment without knowing a k…