Projects

Culture

We strive to build an interdisciplinary team working in the areas of natural language processing and human-computer interaction. Our core values are:

  • Experimental: We value scientific rigor, focusing on researching under strong scientific grounds and conducting sound experiments that provide definitive and repeatable findings.
  • Computational: Our scientific nature is to use algorithms, mathematical models, strong theoretical background, and strong coding skills.

Lab Entry

We welcomed students from all disciplines but those with a huge passion for research.

Problems we are interested

  1. Small Language Models
    Small Language Models: SLM has the potential to reduce costs and improve ease for edge deployment. This project aims to develop datasets, tools, and techniques to enable us to successfully develop small language models.
  2. Avatar & Voice Cloning
    Avatar | Voice Cloning | Text2Speech: Voice cloning or avatar generation or text2speech are extremely useful in the domain of education and tourism. This project aims to develop datasets and techniques to enable us to engineer effective solutions.
  3. LLM Human Understanding
    LLM that truly understands humans: How can we develop LLM that is emotionally intelligent, and that can serve human beings by understanding their beliefs, cognition, behaviors, culture, and biases, etc.?
  4. Multimodal LLM
    Multimodal LLM: Related to above, can we improve the capabilities of LLM by combining other modalities such as voice and face, for example, to detect depression, confidence, humours, or risk profiles?
  5. Medical VQA
    Medical VQA: Can we create an intelligent system that, given input of medical images, provide explainable responses to complex inquiries? Such system can potentially train radiologist trainees as well as provide second opinions to general radiologists.
  1. Raman Spectroscopy
    Raman Spectroscopy: How to measure blood glucose non-invasively using Raman spectroscopy? Can we put them into a portable low-cost machine and deploy them into households?
  2. EEG BCI Speller
    EEG BCI Speller: How to develop an effective and user-friendly BCI speller for locked-in patients using EEG?
  3. Chatbot for emotional support
    Chatbot for emotional support: Can we incorporate CBT/DBT/ACT to chatbot to provide emotional support or assessments to people suffering from stress or depression?