Zhaofeng (Philip) WangHi! My name is Philip Wang. I am a Research Assistant in the IDEAS Lab at Northwestern University, supervised by Prof. Qi Zhu. I received my B.A. in Mathematics and Psychology from Northwestern University. During undergrad, I have also had the pleasure of receiving a summer research fund to work with Prof. Zach Wood-Doughty in 2024. I have a broad interest at the intersection of reinforcement learning, formal methods, and control for safe autonomous systems. I am excited about integrating formal verification and control-theoretic tools with learning-based methods to obtain safe, interpretable, and scalable embodied agents. If you are interested in any aspect of me, I am always open to discussions and academic collaborations. Feel free to reach out to me at — philipwang2025 [at] u [dot] northwestern [dot] edu GitHub / Google Scholar / CV |
|
|
|
SENTINEL: A Multi-Level Formal Framework for Safety Evaluation of LLM-based Embodied AgentsSimon Sinong Zhan *, Yao Liu *, Philip Wang *, Zinan Wang, Qineng Wang, Zhian Ruan, Xiangyu Shi, Xinyu Cao, Frank Yang, Kangrui Wang, Huajie Shao, Manling Li, Qi Zhu Under Review, 2025. arXiv |
|
Belief-Based Offline Reinforcement Learning for Delay-Robust Policy OptimizationSimon Sinong Zhan, Qingyuan Wu, Philip Wang, Frank Yang, Xiangyu Shi, Chao Huang, Qi Zhu Under Review, 2025. arXiv |
|
Enhancing Inverse Reinforcement Learning through Encoding Dynamic Information in Reward ShapingSimon Sinong Zhan *, Philip Wang *, Qingyuan Wu, Yixuan Wang, Ruochen Jiao, Chao Huang, Qi Zhu Under Review, 2025. arXiv |
|
Inverse Delayed Reinforcement LearningSimon Sinong Zhan *, Qingyuan Wu *, Aria Ruan, Frank Yang, Philip Wang, Yixuan Wang, Ruochen Jiao, Chao Huang, Qi Zhu arXiv, 2024. arXiv |
|
|