About Me

Hello! I’m Chenyi Xu, currently a forth-year undergraduate at Hangzhou Dianzi University. I’m very fortunate to be advised by Prof. Liqi Yan at HDU, and in 2025 I was briefly supervised at the AGI Lab at Westlake University under Prof. Chi Zhang. I am currently a research intern at the HAI Lab at Eastern Institute of Technology under Prof. Wentao Zhu. I am actively seeking master’s or PhD opportunities for Fall 2027.

My research interests lie in Computer Graphics and Embodied Intelligence — how to make 3D content creation faster and more accessible, how embodied agents can better understand and navigate real-world (or augmented) environments, and how vision-language models can bridge perception and action. I enjoy the full research cycle, from reading papers and brainstorming ideas to implementing and evaluating prototypes, and I believe combining strong geometric understanding with modern foundation models opens up exciting possibilities.

Outside of research, I like Mahjong, poker, hiking, traveling, and listening to podcasts. Feel free to reach out if you’d like to connect!

Publications

1. LongDPM: Overlap-Aware 4D Reconstruction from Long Monocular Videos
   Chenyi Xu, Yihao Wu, Liqi Yan†, Chao Yang, Jianhui Zhang, Fangli Guan, Pan Li
   arXiv:2605.17303

2. Fast3Dcache: Training-free 3D Geometry Synthesis Acceleration
   Mengyu Yang, Yanming Yang, Chenyi Xu, Chenxi Song, Yufan Zuo, Tong Zhao, Ruibo Li, Chi Zhang†
   Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR-26), Poster Presentation, 2026

3. AR-Nav Benchmark: Augmented Reality Navigation with Vision and Language
   Liqi Yan†, Yihao Wu, Chenyi Xu, Chao Yang, Jianhui Zhang, Pan Li
   Proceedings of the AAAI Conference on Artificial Intelligence (AAAI-26), Oral Presentation, 2026

4. ShapeNav: 3D Geometric Perception and Reasoning for Multi-Floor Vision-and-Language Navigation
   Yihao Wu, Chenhuan Cai, Liqi Yan†, Mingxiang Li, Chenyi Xu, Chao Yang, Fangli Guan, Pan Li
   Proceedings of the ACM International Conference on Multimedia 2026 (ACM MM 2026), Oral Presentation, 2026

5. BrainNav: Towards Dual-Brain Minimal Sufficient Representation for Vision-Language Navigation
   Yihao Wu*, Chenyi Xu*, Liqi Yan†, Chenhuan Cai, Geyong Min, Bin Lin, Fangli Guan, Jianhui Zhang, Pan Li arXiv:2607.23181

News

• November 2025
  Very excited that our paper AR-Nav Benchmark has been accepted to AAAI 2026 as an Oral presentation! Huge thanks to all co-authors and especially to my advisor for the support throughout the project.

• April 2025
  Joined the PARK project (University of Rochester) as a remote contributor. We built a web-based application that analyzes participants’ movements, speech, and facial expressions to help assess symptoms related to Parkinson’s disease.

• June – September 2025
  Spent an unforgettable summer doing research at AGI Lab, Westlake University. Learned a tremendous amount from my advisor Prof. Chi Zhang and wonderful senior lab mates. Grateful for all the guidance, discussions, and late-night debugging sessions.

• March 2025
  Received the University First-Class Scholarship for academic performance.

• September 2024
  Awarded Provincial First Prize in the National College Students Mathematical Contest in Modeling (MCM/ICM).

If you’re working on something related to 3D generation, embodied agents, AR/VR navigation, vision-language models, or you just enjoy a good round of Mahjong, I’d love to hear from you!