avatar

Yuanhuiyi Lyu吕原汇一

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


About Me

Hi! I'm Yuanhuiyi Lyu (吕原汇一), 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. I am currently a research intern at Kling AI, Kuaishou, where I work on multimodal generation.

Currently, I focus on:

Thinking for Multimodal Understanding and Generation
  • CoT data for multimodal pre-training/post-training
  • Thinking in image/video generation
  • RL for image/video generation
Harness for Multimodal Generation
  • Web search/RAG for image/video generation
  • Agentic Loop for image/video generation

>>> I am currently on the job market and open to research or engineering opportunities in multimodal AI. Please feel free to contact me by email.

Selected Publications

Please refer to my Google Scholar for a full paper list.

Research Direction 1

Thinking for Multimodal Understanding and Generation

  • CoT data for multimodal pre-training/post-training
  • Thinking in image/video generation
  • RL for image/video generation
Research Direction 2

Harness for Multimodal Generation

  • Web search/RAG for image/video generation
  • Agentic Loop for image/video generation

Research Experiences

Kling AI

May 2026 - Present
Kuaishou
Research Intern
Contributions to Kling Omni Model
  • Multimodal generation

Ming Team

Dec. 2025 - Apr. 2026
Ant Group
Research Intern
Contributions to Ming-Flash-Omni
  • CoT data for multimodal understanding and generation
  • Reward model for omni-model
  • RL for omni-model

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

Honors and Awards