General world models represent a crucial pathway toward achieving Artificial General
Intelligence (AGI), serving as the cornerstone for various applications ranging from virtual …

The rise of large foundation models, trained on extensive datasets, is revolutionizing the
field of AI. Models such as SAM, DALL-E2, and GPT-4 showcase their adaptability by …

We introduce a self-supervised pretraining method called OccFeat for camera-only Bird's-
Eye-View (BEV) segmentation networks. With OccFeat we pretrain a BEV network via …

Improving the detection of distant 3d objects is an important yet challenging task. For camera-
based 3D perception the annotation of 3d bounding relies heavily on LiDAR for accurate …

World models can foresee the outcomes of different actions, which is of paramount
importance for autonomous driving. Nevertheless, existing driving world models still have …

Representation learning approaches for robotic manipulation have boomed in recent years.
Due to the scarcity of in-domain robot data, prevailing methodologies tend to leverage large …

Using generative models to synthesize new data has become a de-facto standard in
autonomous driving to address the data scarcity issue. Though existing approaches are able …

World models are receiving increasing attention in autonomous driving for their ability to
predict potential future scenarios. In this paper, we present BEVWorld, a novel approach that …

Video is a particularly universal and scalable target given a wealth of uncalibrated driving
videos. Different from BEV representations [25, 37] that require camera extrinsic parameters …

This technical report summarizes the second-place solution for the Predictive World Model
Challenge held at the CVPR-2024 Workshop on Foundation Models for Autonomous …