Ph.D. Candidate @ UM

Yiming Wang 王一鸣

I am currently a Ph.D. Candidate in State Key Laboratory of Internet of Things for Smart City (University of Macau), fortunate to be advised by Prof. Leong Hou U, Ryan. I also had worked with Prof. Bo An , Prof. Steven Morad , and Prof. Jiayu Chen . Before joining UM, I obtained my bachelor's degree from the Department of Computing and Information Science at Harbin Institute of Technology (HIT) in 2020. I am interested in improving the efficiacy and generalization of autonomous agents using simulation, reinforcement learning, and causal discovery.

I am passionate about pursuing research that is both practically impactful or scientifically interesting.
(Recruiting) Always open to collaborators.

Latest Updates

2025.11 Four papers accepted to AAAI 2026, one selected as oral presentation.
2025.10 I began my research visit to the AI-for-X Lab at Nanyang Technological University (NTU).
2025.04 Two papers accepted to IJCAI 2025.
2025.02 Paper on HeMoRa accepted to CVPR 2025.
2024.09 Paper on rethinking exploration published as spotlight in NeurIPS 2024.
2023.12 My team wins First Prize Award of 8th Greater Bay Area IT Application System Development Competition
2023.11 My poster wins the Third Prize Poster Award of MCSCT.
2023.09 Our paper on exploration in RL was accepteded in NeurIPS 2023.
2023.07 Our paper on RL for traffic light control was accepted to IEEE Transactions on Industrial Informatics.
2023.07 Our paper on multi agent communication was accepted to DASFAA.

Selected Publications

*: I am the co-first author, †: corresponding author

Explore to Learn: Latent Exploration through Disentangled Synergy Patterns for RL in Overactuated Control

Yiming Wang, Kaiyan Zhao, Xu Li, Yan Li, Jiayu Chen, Steven Morad, Leong Hou U

AAAI 2026 Oral

Paper Code BibTeX

Rethinking Exploration in Reinforcement Learning with Effective Metric-Based Exploration Bonus

Yiming Wang, Kaiyan Zhao, Furui Liu, Leong Hou U

NeurIPS 2024 spotlight (top 2%)

OpenReview Code BibTeX

Latent State-Predictive Exploration for Deep Reinforcement Learning

Yiming Wang, Kaiyan Zhao, Borong Zhang, Yan Li, Leong Hou U

AAAI 2026

Paper Code BibTeX

DSAP: Enhancing Generalization in Goal-Conditioned Reinforcement Learning

Yiming Wang, Kaiyan Zhao, Ming Yang, Yan Li, Furui Liu, Jiayu Chen, Leong Hou U

AAAI 2026

Paper Code BibTeX

Efficient Potential-based Exploration in Reinforcement Learning using Inverse Dynamic Bisimulation Metric

Yiming Wang, Ming Yang, Renzhi Dong, Binbin Sun, Furui Liu, Leong Hou U

NeurIPS 2023

OpenReview Code BibTeX

BILE: An Effective Behavior-based Latent Exploration Scheme for Deep Reinforcement Learning

Yiming Wang, Kaiyan Zhao, Yan Li, Leong Hou U

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

CVPR 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

IJCAI 2025

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

arXiv Code BibTeX

Team-wise Effective Communication in Multi-Agent Reinforcement Learning

Ming Yang, Kaiyan Zhao, Yiming Wang, Renzhi Dong, Yali Du, F Liu, M Zhou, Leong Hou U

AAMAS 2024

DOI Code BibTeX

Conference Reviewer: ICML, ICLR, NeurIPS, AISTATS, CoRL, IJCAI, ICASSP, DASFAA, KDD, AAAI

Journal Reviewer: TMLR, IEEE TNNLS, IEEE T-ITS, IEEE Access, IEEE TII, AJCST

Yiming Wang 王一鸣

Latest Updates

Selected Publications

Explore to Learn: Latent Exploration through Disentangled Synergy Patterns for RL in Overactuated Control

Rethinking Exploration in Reinforcement Learning with Effective Metric-Based Exploration Bonus

Latent State-Predictive Exploration for Deep Reinforcement Learning

DSAP: Enhancing Generalization in Goal-Conditioned Reinforcement Learning

Efficient Potential-based Exploration in Reinforcement Learning using Inverse Dynamic Bisimulation Metric

BILE: An Effective Behavior-based Latent Exploration Scheme for Deep Reinforcement Learning

HeMoRa: Unsupervised Heuristic Consensus Sampling for Robust Point Cloud Registration

Efficient Diversity-based Experience Replay for Deep Reinforcement Learning

Enhancing LLM Agents for Code Generation with Possibility and Pass-rate Prioritized Experience Replay

Team-wise Effective Communication in Multi-Agent Reinforcement Learning

Academic Services