reposiTUm: Per-Group Error, Not Total MSE: Fine-Tuning Vision-Language-Action Models for 11-DoF Mobile Manipulation

Record link:

http://hdl.handle.net/20.500.12708/229483
https://doi.org/10.34726/12403

Title:

Per-Group Error, Not Total MSE: Fine-Tuning Vision-Language-Action Models for 11-DoF Mobile Manipulation

Citation:

Montagut Bofi, P., Blasco, M. G., Pulli, T., & Vincze, M. (2026). Per-Group Error, Not Total MSE: Fine-Tuning Vision-Language-Action Models for 11-DoF Mobile Manipulation [Conference Presentation]. From Data to Decisions: VLA Pipelines for Real Robots (Part of: IEEE International Conference on Robotics and Automation (ICRA 2026)), Austria. https://doi.org/10.34726/12403

reposiTUm DOI:

10.34726/12403

Publication Type:

Presentation - Conference Presentation

Language:

English

Authors:

Montagut Bofi, Pau
Blasco, Mario García
Pulli, Tessa
Vincze, Markus

Organisational Unit:

E376-02 - Forschungsbereich Komplexe Dynamische Systeme

Date (published):

2026