Zhongyi Cai

3345 Engineering Building

428 S. Shaw Lane

East Lansing, MI 48824, U.S.A.

About Me

I am Zhongyi Cai, a Ph.D. student at Computer Science and Engineering Department (CSE) in Michigan State University (MSU), advised by Prof. Yu Kong.

Prior to my Ph.D. endeavor, I obtained my Bachelor’s degree in 2021 and Master’s degree in 2024 at ShanghaiTech University, where I was supervised by Prof. Jingya Wang and Prof. Ye Shi.

Research Interest

My research interest focuses on Spatial Reasoning and Exploration in Embodied AI with Multi-modal Language Models.

Before that, I worked on Few-Shot Learning (FSL) and Federated Learning (FL). I am always welcome to research cooperation! So, if you are interested, feel free to contact me via email.

news

Sep 18, 2025	One paper IndustryEQA accepted by NeurIPS DB Track!
Aug 26, 2024	My exciting Ph.D. endeavor at MSU begins!
Jan 16, 2024	One paper accepted by ICLR!
Sep 22, 2023	One paper on Non-IID Federated Learning accepted by NeurIPS!
Apr 08, 2023	One paper accepted by IEEE Transactions on Neural Networks and Learning Systems (TNNLS)!

selected publications

Vision to Geometry: 3D Spatial Memory for Sequential Embodied MLLM Reasoning and Exploration

Zhongyi Cai#, Yi Du#, Chen Wang, and Yu Kong

Under Review, 2026

PDF
Open Set Face Forgery Detection via Dual-Level Evidence Collection

Zhongyi Cai, Bryce Gernon, Wentao Bao, Yifan Li, Matthew Wright, and Yu Kong

Under Review, 2025

PDF Website
IndustryEQA: Pushing the Frontiers of Embodied Question Answering in Industrial Scenarios

Yifan Li#, Yuhang Chen#, Anh Dao#, lichi Li, Zhongyi Cai, Zhen Tan, Tianlong Chen, and Yu Kong

Advances in Neural Information Processing Systems DB Track, 2025

PDF Code

Fed-CO2: Cooperation of Online and Offline Models for Severe Data Heterogeneity in Federated Learning

Zhongyi Cai, Ye Shi, Wei Huang, and Jingya Wang

Advances in Neural Information Processing Systems, 2023

Bib PDF Code Poster Slides

@article{cai2024fed,
  title = {Fed-CO2: Cooperation of Online and Offline Models for Severe Data Heterogeneity in Federated Learning},
  author = {Cai, Zhongyi and Shi, Ye and Huang, Wei and Wang, Jingya},
  journal = {Advances in Neural Information Processing Systems},
  volume = {36},
  year = {2023},
}

Fedtp: Federated learning by transformer personalization

Hongxia Li#, Zhongyi Cai#, Jingya Wang, Jiangnan Tang, Weiping Ding, Chin-Teng Lin, and Ye Shi

IEEE transactions on neural networks and learning systems, 2023

Bib PDF Code

@article{li2023fedtp,
  title = {Fedtp: Federated learning by transformer personalization},
  author = {Li#, Hongxia and Cai#, Zhongyi and Wang, Jingya and Tang, Jiangnan and Ding, Weiping and Lin, Chin-Teng and Shi, Ye},
  journal = {IEEE transactions on neural networks and learning systems},
  year = {2023},
  publisher = {IEEE},
}