Bingbing Liu

Robust-WAM achieves superior out-of-distribution generalization in robot control by seamlessly integrating semantic foresight into action predictions while leveraging extensive VGM pretraining.

Animatable 3D vehicle models can now be generated from single images, enabling more realistic autonomous driving simulations that capture part-level articulation like wheel steering and door opening.

Pre-training with Dual Latent World Models unlocks significant performance gains in autonomous driving tasks by learning holistic Gaussian-centric representations.