CARVIEW

MOTORHOMES

Select Language

HTTP/2 200 server: GitHub.com content-type: text/html; charset=utf-8 last-modified: Fri, 31 Oct 2025 05:46:45 GMT access-control-allow-origin: * strict-transport-security: max-age=31556952 etag: W/"69044d45-48f3" expires: Wed, 31 Dec 2025 00:57:17 GMT cache-control: max-age=600 content-encoding: gzip x-proxy-cache: MISS x-github-request-id: 26FE:318CF6:A88F9B:BDA5EC:69547293 accept-ranges: bytes age: 0 date: Wed, 31 Dec 2025 00:47:17 GMT via: 1.1 varnish x-served-by: cache-bom-vanm7210075-BOM x-cache: MISS x-cache-hits: 0 x-timer: S1767142037.243593,VS0,VE225 vary: Accept-Encoding x-fastly-request-id: 63f2958eaa5da213df13cfebfc5bc3c4f01c9abe content-length: 4073 Ryan, Yuanhuiyi LYU

Ryan, Yuanhuiyi LYU

Ph.D. Student
The Hong Kong University of Science and Technology
ryan.lyu.mail@gmail.com

About Me

Hi! I’m (Ryan) Yuanhuiyi Lyu, a Ph.D. student in Artificial Intelligence at The Hong Kong University of Science and Technology (Guangzhou). I am fortunate to be advised by Prof. Xuming Hu, Prof. Linfeng Zhang @ SJTU, and Prof. Ying-Cong Chen. Previously, I obtained my B.ENG in Artificial Intelligence from Northeastern University, advised by Prof. Zhenghao Liu

Currently, I focus on:

Multimodal Learning & Reasoning: Multimodal alignment, Understanding-Generation interaction.
Visual Generation: Retrieval-augmented visual generation, X-to-Image generation.

Selected Publications

Google Scholar

Multimodal Learning & Reasoning

Understanding-in-Generation: Reinforcing Generative Capability of Unified Model via Infusing Understanding into Generation

Yuanhuiyi Lyu, Chi-Kit Wong, Chenfei Liao, Lutao Jiang, Xu Zheng, Zexin Lu, Linfeng Zhang, Xuming Hu

arXiv (arXiv), 2025.

Code PDF
Visual Generation

RealRAG: Retrieval-augmented Realistic Image Generation via Self-reflective Contrastive Learning

Yuanhuiyi Lyu, Xu Zheng, Lutao Jiang, Yibo Yan, Xin Zou, Huiyu Zhou, Linfeng Zhang, Xuming Hu

Forty-Second International Conference on Machine Learning(ICML), 2025.

Homepage PDF
Multimodal Learning & Reasoning

UniBind: LLM-Augmented Unified and Balanced Representation Space to Bind Them All

Yuanhuiyi Lyu, Xu Zheng, Jiazhou Zhou, Lin Wang

The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024.

Code PDF
Visual Generation

Image Anything: Towards Reasoning-coherent and Training-free Multi-modal Image Generation

Yuanhuiyi Lyu, Xu Zheng, Lin Wang

arXiv (arXiv), 2024.

Homepage PDF
Multimodal Learning & Reasoning

Learning Modality-agnostic Representation for Semantic Segmentation from Any Modalities

Xu Zheng, Yuanhuiyi Lyu, Lin Wang

The European Conference on Computer Vision (ECCV), Oral, 2024.

Homepage PDF
Multimodal Learning & Reasoning

Universal Vision-Language Dense Retrieval: Learning A Unified Representation Space for Multi-Modal Retrieval

Zhenghao Liu, Chenyan Xiong, Yuanhuiyi Lv, Zhiyuan Liu, Ge Yu

The Eleventh International Conference on Learning Representations (ICLR), 2023.

Code PDF

Honors and Awards

2023.07 Outstanding Graduation Dissertation (<2%), Northeastern University.
2022.09 Outstanding Students Scholarship, Northeastern University.
2021.09 Outstanding Students Scholarship, Northeastern University.
2020.09 Outstanding Students Scholarship, Northeastern University.

Internships

[Jul. 2023 ‑ Sep. 2024], VLIS Lab, The Hong Kong University of Science and Technology
- Supervisor: Lin Wang
[Oct. 2021 ‑ Feb. 2023], THUNLP Lab, Tsinghua University
- Supervisor: Zhenghao Liu, Chenyan Xiong, and Zhiyuan Liu

Education

Ph.D. in Artificial Intelligence

The Hong Kong University of Science and Technology (Guangzhou)

2024 – Present

B.ENG in Artificial Intelligence

Northeastern University (Shenyang)

2019 – 2023

Services

Reviewer:
- Conferences: CVPR, ECCV, ICCV, ICLR, ICML, NeurIPS, WACV, AAAI
- Journals: IJCV, TIP
Teaching Assistant:
- RBCC, Red Bird Challenge Camp, HKUST Guangzhou, 2025.07-2025.08
- UFUG2104, Applied Statistics, HKUST Guangzhou, 2025.02-2025.06

Original Source | Taken Source