MAG: Multi-Modal Aligned Autoregressive Co-Speech Gesture Generation without Vector Quantization.

VRsketch2Gaussian: 3D VR Sketch Guided 3D Object Generation with Gaussian Splatting.

GaussianGrasper: 3D Language Gaussian Splatting for Open-Vocabulary Robotic Grasping.

DOME: Taming Diffusion Model into High-Fidelity Controllable Occupancy World Model.

HE-Drive: Human-Like End-to-End Driving with Vision Language Models.

Text2Street: Controllable Text-to-image Generation for Street Views.

ASSIST: Interactive Scene Nodes for Scalable and Realistic Indoor Simulation.

A Multi-Granularity Information-Based Method for Learning High-Dimensional Bayesian Network Structures.