About
I am a research intern at NTU, advised by Prof. Yang Liu. Previously, I was a research intern at UIUC, working with Prof. Tong Zhang, and a visiting student at Rutgers University, advised by Prof. Hao Wang. I obtained my B.S. in Electronic Information Engineering from Wuhan University.
My research focuses on multimodal learning, world models, and embodied AI, with an emphasis on building AI systems that reason over visual, physical, and temporal structure to interact with the real world.
Selected Publications
View All →PhysMRV: Physical Memory Retrieval and Verification for Physics Plausibility Reasoning
Wenyuan Wang, Lianyu Hu, Minghao Fu, Hao Wang, Yang Liu
arXiv preprint (2026)
A training-free retrieval-augmented reasoning framework with a hierarchical Physical Memory Bank built from 19,708 video-QA examples for physical plausibility reasoning.
Probabilistic Residual Learning for Online Recommendations
Wenyuan Wang†, Yusong Zhao†, Zihao Xu, Hengyi Wang, Shreya Venugopal, Desmond Lobo, Chengzhi Mao, Qi Xu, Zhigang Hua, Yan Xie, Bo Long, Shuang Yang, Hao Wang
RecSys 2026
PRUC is a causal Bayesian framework that clusters users and models residuals to enhance recommendation accuracy and cold-start performance.
Generalizable Geometric Image Caption Synthesis
Yue Xin†, Wenyuan Wang†, Rui Pan, Ruida Wang, Howard Meng, Renjie Pi, Shizhe Diao, Tong Zhang
arXiv preprint arXiv:2509.15217
Integrated symbolic reasoning with neural-guided heuristics for geometric problem-solving and image generation
PhysProver: Advancing Automatic Theorem Proving for Physics
Hanning Zhang†, Ruida Wang†, Rui Pan†, Wenyuan Wang†, BingXu Meng, Tong Zhang
arXiv preprint arXiv:2601.15737; under review at EMNLP 2026
Curated dataset of 3,122 training examples from PhysLean library and proposed evaluation framework using Lean server verification for physics theorem proving