32 citations · 36 across the 9 of their papers we have counts for
6 papers · 1 filter
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)…
MamMA: A Mamba-Based Pedestrian Trajectory Prediction Algorithm Considering Occupancy Map and Pedestrian Awareness States
Juncen Long, Xiaofeng Jin, Gianluca Bardaro +2
Many pedestrian trajectory prediction algorithms have been proposed to improve the safety of navigation for mobile robots working in human-robot coexistence environments. Some pede…
Multimodal Behavior Tree Generation: A Small Vision-Language Model for Robot Task Planning
Cristiano Battistini, Riccardo Andrea Izzo, Gianluca Bardaro +1
Large language models have been widely used for robotic task planning, often taking advantage of representations such as Behavior Trees (BTs). Vision-Language Models (VLMs) have ex…
Act, Think or Abstain: Complexity-Aware Adaptive Inference for Vision-Language-Action Models
Riccardo Andrea Izzo, Gianluca Bardaro, Matteo Matteucci
Current research on Vision-Language-Action (VLA) models predominantly focuses on enhancing generalization through reasoning techniques. While effective, these improvements increase…
BTGenBot-2: Efficient Behavior Tree Generation with Small Language Models
Riccardo Andrea Izzo, Gianluca Bardaro, Matteo Matteucci
Recent advances in robot learning increasingly rely on LLM-based task planning, leveraging their ability to bridge natural language with executable actions. While prior works showc…
Improving Robustness of Vision-Language-Action Models by Restoring Corrupted Visual Inputs
Daniel Yezid Guarnizo Orjuela, Leonardo Scappatura, Veronica Di Gennaro +3
Vision-Language-Action (VLA) models have emerged as a dominant paradigm for generalist robotic manipulation, unifying perception and control within a single end-to-end architecture…