Bolei Zhou

Joint Optimization for 4D Human-Scene Reconstruction in the Wild

From Seeing to Experiencing: Scaling Navigation Foundation Models with Reinforcement Learning

UrbanVerse: Scaling Urban Simulation by Watching City-Tour Videos

SceneStreamer: Continuous Scenario Generation as Next Token Group Prediction

Dreamland: Hybrid World Creation with Simulator and Generative Models

QuantV2X: A Fully Quantized Multi-Agent System for Cooperative Perception

MetaUrban: An Embodied AI Simulation Platform for Urban Micromobility

Predictive Preference Learning from Human Interventions

Learning to Generate Diverse Pedestrian Movements from Web Videos with Noisy Labels

WOMD-Reasoning: A Large-Scale Dataset for Interaction Reasoning in Driving

Bidirectional Motion Transformer for Safety-Critical Traffic Scenario Generation

AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuning

3DitScene: Editing Any Scene via Language-guided Disentangled Gaussian Splatting

Robot-Gated Interactive Imitation Learning with Adaptive Intervention Mechanism

Hyper: Hyperparameter Robust Efficient Exploration in Reinforcement Learning