Bolei Zhou

University of California, Los Angeles — United States

Computer Science · Physical Sciences

65h-index40.8kcitations262works4.82yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Generative Adversarial Networks and Image Synthesis(61), Advanced Image and Video Retrieval Techniques(50), Advanced Neural Network Applications(36), Multimodal Machine Learning Applications(34), Advanced Vision and Imaging(33)

Publications262 total

AnimaMimic: Imitating 3D Animation from Video Priors
arXiv (Cornell University)·2025Open Access
Group Diffusion: Enhancing Image Generation by Unlocking Cross-Sample Collaboration
arXiv (Cornell University)·2025Open Access
CooPre: Cooperative Pretraining for V2X Cooperative Perception
2025· 1 cited
UrbanVerse: Scaling Urban Simulation by Watching City-Tour Videos
arXiv (Cornell University)·2025Open Access
Predictive Preference Learning from Human Interventions
arXiv (Cornell University)·2025Open Access
TurboTrain: Towards Efficient and Balanced Multi-Task Learning for Multi-Agent Perception and Prediction
arXiv (Cornell University)·2025Open Access
InfGen: Scenario Generation as Next Token Group Prediction
arXiv (Cornell University)·2025Open Access
AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuning
arXiv (Cornell University)·2025Open Access
Adv-BMT: Bidirectional Motion Transformer for Safety-Critical Traffic Scenario Generation
arXiv (Cornell University)·2025Open Access
Towards Autonomous Micromobility through Scalable Urban Simulation
2025
Embodied Scene Understanding for Vision Language Models via MetaVQA
2025· 2 cited
Vid2Sim: Realistic and Interactive Simulation from Video for Urban Navigation
2025· 5 cited
Robot-Gated Interactive Imitation Learning with Adaptive Intervention Mechanism
arXiv (Cornell University)·2025Open Access
Data-Efficient Learning from Human Interventions for Mobile Robots
2025· 1 cited
X-Fusion: Introducing New Modality to Frozen Large Language Models
arXiv (Cornell University)·2025Open Access
BEVCon: Advancing Bird's Eye View Perception With Contrastive Learning
IEEE Robotics and Automation Letters·2025· 1 cited
Learning from Active Human Involvement through Proxy Value Propagation
arXiv (Cornell University)·2025· 1 citedOpen Access
Embodied Scene Understanding for Vision Language Models via MetaVQA
arXiv (Cornell University)·2025Open Access
Vid2Sim: Realistic and Interactive Simulation from Video for Urban Navigation
arXiv (Cornell University)·2025Open Access
Joint Optimization for 4D Human-Scene Reconstruction in the Wild
arXiv (Cornell University)·2025Open Access
page 1 of 14Next →

Frequent Co-authors

Antonio Torralba(20), Aude Oliva(12), Xiaogang Wang(10), Àgata Lapedriza(9), Aditya Khosla(7), Xiaoou Tang(6), David Bau(6), Yujun Shen(5), Jianping Shi(4), Hang Zhao(3), Xavier Puig(3), Sanja Fidler(3), Adela Barriuso(3), Tete Xiao(3), Wanli Ouyang(3), Liangji Fang(3), Qinhong Jiang(3), Jun-Yan Zhu(3), Hendrik Strobelt(3), Alex Andonian(2)