Multimodal Understanding & Generation
I bridge the gap between vision and language, building AI systems that can see, understand, and create.
| Role | Organization | Focus |
|---|---|---|
| Algorithm Expert | Alibaba Cloud | Multimodal AI, Cloud Intelligence |
| Eng.D Student | Zhejiang University | Research & Innovation |
| NLP Researcher | Institute of Computer Innovation Technology | Intent Recognition, Text2SQL, Math Problem-Solving |
- Eng.D β Zhejiang University (Current)
- Postgraduate β The Hong Kong Polytechnic University (Grammar Correction)
π Natural Language Processing
βββ Intent Recognition
βββ Text2SQL
βββ Mathematical Problem-Solving
βββ Grammar Correction
πΌοΈ Multimodal AI
βββ Video Understanding
βββ Vision-Language Models
βββ Generative AI
- π§ Email: younglishimin@gmail.com
- π LinkedIn: linkedin.com/in/yangjun-wu-802285b6
- π Google Scholar: My Publications
"Code is like humor. When you have to explain it, it's bad." β Cory House