MindJourney: Test-Time Scaling with World Models for Spatial Reasoning

TL;DR

MindJourney introduces a test-time scaling framework that enhances vision-language models with a controllable world model for improved 3D spatial reasoning without fine-tuning, demonstrated by performance gains on the SAT benchmark.

Contribution

The paper presents a novel test-time scaling approach coupling VLMs with a video diffusion-based world model for robust 3D spatial reasoning.

Findings

Achieves over 7.7% performance boost on SAT benchmark.

Improves VLM reasoning without fine-tuning.

Demonstrates effectiveness of world models for test-time scaling.

Abstract

Spatial reasoning in 3D space is central to human cognition and indispensable for embodied tasks such as navigation and manipulation. However, state-of-the-art vision-language models (VLMs) struggle frequently with tasks as simple as anticipating how a scene will look after an egocentric motion: they perceive 2D images but lack an internal model of 3D dynamics. We therefore propose MindJourney, a test-time scaling framework that grants a VLM with this missing capability by coupling it to a controllable world model based on video diffusion. The VLM iteratively sketches a concise camera trajectory, while the world model synthesizes the corresponding view at each step. The VLM then reasons over this multi-view evidence gathered during the interactive exploration. Without any fine-tuning, our MindJourney achieves over an average 7.7% performance boost on the representative spatial reasoning benchmark SAT, showing that pairing VLMs with world models for test-time scaling offers a simple, plug-and-play route to robust 3D reasoning. Meanwhile, our method also improves upon the test-time inference VLMs trained through reinforcement learning, which demonstrates the potential of our method that utilizes world models for test-time scaling.