Xiaoyang Guo

MVGE: Scale-invariant and Temporal-consistent Monocular Video Geometry Estimation

RAD: Training an End-to-End Driving Policy via Large-Scale 3DGS-based Reinforcement Learning

Boost 3D Reconstruction using Diffusion-based Intrinsic Estimation

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

DrivingWorld: Constructing World Model for Autonomous Driving via Video GPT

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

OccVAR: Scalable 4D Occupancy Prediction via Next-Scale Prediction