Boyi Li

Latest

• DreamDrive: Generative 4D Scene Modeling from Street View Images
• STORM: Spatio-Temporal Reconstruction Model for Large-Scale Outdoor Scenes
• LoRA3D: Low-Rank Self-Calibration of 3D Geometric Foundation Models
• Promptable Closed-loop Traffic Simulation
• Tokenize the World into Object-level Knowledge to Address Long-tail Events in Autonomous Driving
• Driving Everywhere with Large Language Model Policy Adaptation
• DiffuBox: Refining 3D Object Detection with Point Diffusion
• Language-Image Models with 3D Understanding
• EmerNeRF: Emergent Spatial-Temporal Scene Decomposition via Self-Supervision