Bolei Zhou

14

Papers

61

Total Citations

Papers (14)

Vid2Sim: Realistic and Interactive Simulation from Video for Urban Navigation

V2XPnP: Vehicle-to-Everything Spatio-Temporal Fusion for Multi-Agent Perception and Prediction

X-Fusion: Introducing New Modality to Frozen Large Language Models

BerfScene: Bev-conditioned Equivariant Radiance Fields for Infinite 3D Scene Generation

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

Verbalized Representation Learning for Interpretable Few-Shot Generalization

Towards Text-guided 3D Scene Composition

FreeControl: Training-Free Spatial Control of Any Text-to-Image Diffusion Model with Any Condition

Hyper: Hyperparameter Robust Efficient Exploration in Reinforcement Learning

Towards Autonomous Micromobility through Scalable Urban Simulation

Embodied Scene Understanding for Vision Language Models via MetaVQA

TurboTrain: Towards Efficient and Balanced Multi-Task Learning for Multi-Agent Perception and Prediction

Occupancy Learning with Spatiotemporal Memory

Predictive Preference Learning from Human Interventions