WorldVLM: Combining World Model Forecasting and Vision-Language Reasoning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Englmeier, Stefan, Winter, Katharina, Flohr, Fabian B.
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911521625341952
author Englmeier, Stefan
Winter, Katharina
Flohr, Fabian B.
author_facet Englmeier, Stefan
Winter, Katharina
Flohr, Fabian B.
contents Autonomous driving systems depend on on models that can reason about high-level scene contexts and accurately predict the dynamics of their surrounding environment. Vision- Language Models (VLMs) have recently emerged as promising tools for decision-making and scene understanding, offering strong capabilities in contextual reasoning. However, their limited spatial comprehension constrains their effectiveness as end-to-end driving models. World Models (WM) internalize environmental dynamics to predict future scene evolution. Recently explored as ego-motion predictors and foundation models for autonomous driving, they represent a promising direction for addressing key challenges in the field, particularly enhancing generalization while maintaining dynamic prediction. To leverage the complementary strengths of context-based decision making and prediction, we propose WorldVLM: A hybrid architecture that unifies VLMs and WMs. In our design, the high-level VLM generates behavior commands to guide the driving WM, enabling interpretable and context-aware actions. We evaluate conditioning strategies and provide insights into the hybrid design challenges.
format Preprint
id arxiv_https___arxiv_org_abs_2603_14497
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle WorldVLM: Combining World Model Forecasting and Vision-Language Reasoning
Englmeier, Stefan
Winter, Katharina
Flohr, Fabian B.
Computer Vision and Pattern Recognition
Robotics
Autonomous driving systems depend on on models that can reason about high-level scene contexts and accurately predict the dynamics of their surrounding environment. Vision- Language Models (VLMs) have recently emerged as promising tools for decision-making and scene understanding, offering strong capabilities in contextual reasoning. However, their limited spatial comprehension constrains their effectiveness as end-to-end driving models. World Models (WM) internalize environmental dynamics to predict future scene evolution. Recently explored as ego-motion predictors and foundation models for autonomous driving, they represent a promising direction for addressing key challenges in the field, particularly enhancing generalization while maintaining dynamic prediction. To leverage the complementary strengths of context-based decision making and prediction, we propose WorldVLM: A hybrid architecture that unifies VLMs and WMs. In our design, the high-level VLM generates behavior commands to guide the driving WM, enabling interpretable and context-aware actions. We evaluate conditioning strategies and provide insights into the hybrid design challenges.
title WorldVLM: Combining World Model Forecasting and Vision-Language Reasoning
topic Computer Vision and Pattern Recognition
Robotics
url https://arxiv.org/abs/2603.14497