Model Releases
Target-Bench: Can Video World Models Achieve Mapless Path Planning with Semantic Targets?
arXiv:2511.17792v2 Announce Type: replace Abstract: While recent video world models can generate highly realistic videos, their ability to perform semantic reasoning and planning remains unclear and u
arXiv:2511.17792v2 Announce Type: replace Abstract: While recent video world models can generate highly realistic videos, their ability to perform semantic reasoning and planning remains unclear and unquantified. We introduce Target-Bench, the first benchmark that enables comprehensive evaluation of video world models' semantic reasoning, spatial estimation, and planning capabilities. Target-Bench provides 450 robot-collected scenarios spanning 47 semantic categories, with SLAM-based trajectories serving as motion tendency references. Our benchmark reconstructs motion from generated videos with a metric scale recovery mechanism, enabling the evaluation of planning performance with five complementary metrics that focus on target-approaching capability and directional consistency. Our evaluation result shows that the best off-the-shelf model achieves only a 0.341 overall score, revealing a significant gap between realistic visual generation and semantic reasoning in current video world models. Furthermore, we demonstrate that fine-tuning process on a relatively small real-world robot dataset can significantly improve task-level planning performance.
Related
- DriveLaW:Unifying Planning and Video Generation in a Latent Driving World
- ICAT: Incident-Case-Grounded Adaptive Testing for Physical-Risk Prediction in Embodied World Models
- Latent Chain-of-Thought World Modeling for End-to-End Driving
- INSPATIO-WORLD: A Real-Time 4D World Simulator via Spatiotemporal Autoregressive Modeling
- How Far Are Video Models from True Multimodal Reasoning?
Source: arXiv cs.CV | 2026-04-16