We are excited to share that we preprinte our latest paper: "Foundation Models in Autonomous Driving: A Survey on Scenario Generation and Scenario Analysis".

This work is a joint effort between multiple institutions and industry partners including Technical University of Munich (TUM), Stanford University, Austrian Institute of Technology (AIT), Audi AG, Technical University of Darmstadt, fortiss GmbH and University of the Bundeswehr Munich.

🚗🔬 This comprehensive survey provides an in-depth overview of how Foundation Models (FMs) — including Large Language Models (LLMs), Vision-Language Models (VLMs), Multimodal Large Language Models (MLLMs), Diffusion Models (DMs), and World Models (WMs) — are revolutionizing scenario generation and scenario analysis in autonomous driving.

Key highlights of the paper:

• First systematic survey exclusively dedicated to FM-based scenario generation & analysis.
• Taxonomy of current approaches across multiple FM types.
• Review of publicly available datasets, simulation platforms, and benchmark competitions.
• Identification of key challenges and promising future research directions.

📄 Read the full paper here: https://arxiv.org/pdf/2506.11526 
💻 Explore our code and continuously updated repository: GitHub Repository