ZI-230 / Master Thesis Vision Language Action Models with Memory

ZI-230 / Master Thesis Vision Language Action Models with Memory

THEORETISCH DIE BESTE ENTSCHEIDUNG. PRAKTISCH AUCH.

TEILE DEINE LEIDENSCHAFT.

We, the BMW Group, offer you an interesting and varied master's thesis within the area of memory for VLAs in automated driving. Based on related work on memory usage in LLM/VLMs and VLAs, you will explore how these models can be utilized for reasoning and task execution.

What awaits you?

• Close collaboration in a team within the BMW research department.
• Explore different memory in VLM and VLA approaches for automated driving applications.
• Evaluate several learning and non-learning based memory approaches in automated driving tasks.
• Work on state-of-the-art techniques and develop novel approaches.
• Deploy them in our prototypes for real world testing.

Please note that your thesis must be supervised by a university on your part.

What should you bring along?

• Knowledge in machine learning and computer vision.
• Knowledge in Vision Language Models (VLM) and/or Vision Language Action Models (VLA).
• Experience in memory for language models preferred.
• Proficiency with Python and deep learning frameworks (PyTorch or TensorFlow).

What do we offer?

• Digital offers & mobile working.
• Attractive remuneration.
• Apartment offers for students (subject to availability & only Munich).

You are enthused by new technologies and an innovative environment? Apply now!

At the BMW Group, we see diversity and inclusion in all its dimensions as a strength for our teams. Equal opportunities are a particular concern for us, and the equal treatment of applicants and employees is a fundamental principle of our corporate policy. That is why our recruiting decisions are also based on personality, experience and skills.

ZI-230 / Master Thesis Vision Language Action Models with Memory

BMW AG