Vision-Language-Action AI for Advanced Robotics

ALMA MATER STUDIORUM - UNIVERSITA' DI BOLOGNA - - DIPARTIMENTO DI INFORMATICA - SCIENZA E INGEGNERIA; Italia; On-site; EUR 38,000 - 60,000; Full time

Job summary

ALMA MATER STUDIORUM – UNIVERSITY OF BOLOGNA, Department of Computer Science, Sci Eng invites applications for a research position focusing on Vision-Language-Action (VLA) models and World Models (WMs).

The role involves defining data acquisition specifications for video-action datasets through teleoperation and simulation environments, and the development and training of VLA and WM models.

Responsibilities

• State-of-the-art study of Vision-Language-Action (VLA) Models and World Models (WMs).
• Definition of specifications for the acquisition of video-action datasets through both teleoperation and simulation environments.
• Development and training of VLA and WM models.

Job description

ALMA MATER STUDIORUM – UNIVERSITY OF BOLOGNA, Department of Computer Science, Sci Eng invites applications for a research position focusing on Vision-Language-Action (VLA) models and World Models (WMs).

The role involves defining data acquisition specifications for video-action datasets through teleoperation and simulation environments, and the development and training of VLA and WM models.