Bolei Zhou
Assistant Professor
Computer Science Department, University of California, Los Angeles
Office: 295D, Engineering VI, UCLA
I study interpretable human-AI interaction for computer vision and machine autonomy. I am also interested in understanding various human-centric properties of current AI models beyond their accuracy, such as explainability, interpretability, steerability, generalization, fairness and bias, and safety.
Some of the earlier works I co-authored are Class Activation Mapping (CAM), Places, ADE20K, Network Dissection.
News
| Jun 20, 2022 | 1st Tutorial on Human-Centered AI for Computer Vision is hosted at CVPR’22 in New Orleans. Slides are available there. I gave a talk on Human-AI interaction for computer vision. |
|---|---|
| Apr 19, 2022 | MetaDrive simulator is updated to facilitate research on RL generalizability, safe exploration, and Multi-Agent traffic simulation. Paper is accepted to IEEE TPAMI. |
| Jan 2, 2022 | After wonderful 3 years at CUHK, I moved to UCLA CS to continue my academic journey. |
| Oct 8, 2021 | honored to be in the ICCV Mentors and the PhD Consortium. Come to join Mentorship Social Session. |
| Oct 8, 2021 | I gave a tutorial talk on Human-centric AI at ICCV’21 Tutorial on Trustworthy and Explainable Computer Vision, I also shared the story of my rejection experiences at ICCV@SSLL workshop. |
| Sep 29, 2021 | Two papers are accepted to NeurIPS’21, one on efficient GAN training and the other on Multi-Agent RL. |
| Sep 15, 2021 | Expert Guided Policy Optimization is accepted to the 5th Conference on Robot Learning (CoRL). |
| Sep 10, 2021 |
Homepage is rebuilt through Jekyll 
|
Selected Publications
-
NeurIPS
Exploiting Reward Shifting in Value-Based Deep RLNeural Information Processing Systems (NeurIPS) , 2022 -
CoRL
CoBEVT: Cooperative Bird’s Eye View Semantic Segmentation with Sparse TransformersConference on Robot Learning (CoRL) , 2022
NeurIPS
NeurIPS
ECCV
ECCV Oral
TPAMI
CVPR
CVPR
ICLR
NeurIPS
NeurIPS
CoRL
CVPR Oral
CVPR Oral
IJCV