Kaiyan Zhao ( 赵开延 )
Email: zhao.kaiyan AT whu DOT edu DOT cn
I am a Ph.D. candidate and Research Assistant at the Wuhan University, working at the Institute of Artificial Intelligence. My research focuses on reinforcement learning, automatic control, and graph neural networks. I am passionate about advancing intelligent transportation and autonomous systems to improve safety and efficiency.
News & Updates
2025/04 - Our two paper was published in IJCAI 2025.
2025/02 - Our paper on HeMoRa was published in CVPR 2025.
2024/09 - Our paper on rethinking exploration in reinforcement learning was published as a spotlight in NeurIPS 2024.
2024/09 - I officially began my Ph.D. studies in Computer Science at Wuhan University.
2024/07 - Our paper on team-wise communication was published in Autonomous Agents and Multi-Agent Systems.
2022/08 - Our paper on kernel density visualization was accepted to PVLDB.
Selected Publications
BILE: An Effective Behavior-based Latent Exploration Scheme for Deep Reinforcement Learning
Yiming Wang,
Kaiyan Zhao,
Yan Li, Leong Hou U
34th International Joint Conference on Artificial Intelligence (IJCAI)2025
openreview / code / bibtex
Efficient Diversity-based Experience Replay for Deep Reinforcement Learning
Kaiyan Zhao†,
Yiming Wang†, Yuyang Chen, Yan Li, Leong Hou U, Xiaoguang Niu
34th International Joint Conference on Artificial Intelligence (IJCAI)2025
openreview / code / bibtex
HeMoRa: Unsupervised Heuristic Consensus Sampling for Robust Point Cloud Registration
Shaocheng Yan, Yiming Wang,
Kaiyan Zhao,
Pengcheng S, Zhenjun Z, Yongjun Z, Jiayuan L
Conference on Computer Vision and Pattern Recognition(CVPR) 2025
openreview / code / bibtex
Rethinking Exploration in Reinforcement Learning with Effective Metric-Based Exploration Bonus
Yiming Wang,
Kaiyan Zhao,
Furui Liu, Leong Hou U
Conference on Neural Information Processing Systems(NeurIPS) 2024(Spotlight Top 3%)
openreview / code / bibtex
Enhancing LLM Agents for Code Generation with Possibility and Pass-rate Prioritized Experience Replay
Yuyang Chen†,
Kaiyan Zhao†,
Yiming Wang, Ming Yang, Jian Zhang, Xiaoguang Niu
Preprint
openreview / code / bibtex
AARR-Net: An Attention Assistance Feature Fusion and Model Recursive Recovery Network for Category-level 6D Object Pose Estimation
Haoning Wu,
Kaiyan Zhao,
Shaowu Wu, Xiaoguang Niu and Xiaoping Wu
The International Conference on Neural Information Processing(ICONIP) 2024
DOI / code / bibtex
