The ``LaVi'' (short for Language and Vision) Lab is led by Prof. Liwei Wang in CSE@CUHK. The research focus of this team is to develop AI (NLP and Vision) algorithms that can allow machines to interact with people.

Current research themes are listed below, but not limited to:
1. Language + Vision topics: Visual Grounding/captioning/question answering/reasoning, Embodied AI, and Multimodal applications;
2. NLP Dialogue system and Dialogue related research.
3. Machine Learing + NLP / Computer Vision: to build machine learning models solving computer vision or NLP tasks.
4. Efficient AI, AI for virtual robots, self-supervised learning, learning from the interaction in multimodal environment, etc.
5. Large Language Models.
... ...

To join the team, please contact Prof. Liwei Wang:

We are currently recruiting Phd students, Visiting students, Research Assistants, and Postdocs. Applicants should have excellent background in Computer Vision or Natural Language Processing, or Machine Learning.

For Visiting Students, the minimum length of a visit is 6 months;
For Research Assistants or Interns, the minimum length of this job is 6 months;
For postdocs, the minimum length is 12 months.

LaVi Lab 介绍

这些问题的答案就是我们多模态LaVi 团队要研究的下一代的人工智能交互方式,这也是我们LaVi 团队心中的梦想和使命。
LaVi 和国际上最顶尖的一些工业界实验室有很好的合作关系, 会努力给实验室的学生们提供各种机会;
如果你坚信,我们在不久的将来就可以实现更智能的交互,并且愿意为此付出自己的热情和时间,一起去探索人工智能的星辰大海,那么请联系Prof. Liwei Wang 加入LaVi!