Projects

Culture & Research Philosophy

Our interdisciplinary team works at the cross-section of humans and technologies. Our methodological nature is:

  • Experimental: Conduct reproducible experiments that advance fundamental understanding.
  • Computational: Leverage algorithms, models, and coding expertise to tackle challenging questions.

Lab Entry

We welcome students from all disciplines with strong curiosity and a passion for rigorous, original research. We strive to submit our work to top-tier conferences including ACM CHI, ACL, NIPS, CVPR.

Topics

We focus topics around understanding humans, human well-being, and technologies for better human lives. We are particularly interested in the following research areas:

  1. Mental Health AI Assistant and Trainer
    We are researching how to build AI assistants that can help people with mental health issues. We are particularly interested in understanding the cognitive processes involved in mental health issues, and how to design AI assistants that can provide better support and guidance to users. Example papers: Flash, Comparing Selective Masking Methods for Depression
  2. Mindfulness Technology
    We are researching how to leverage technology to promote mindfulness and well-being. Our work includes developing apps and tools that can help users cultivate present-moment awareness, reduce stress, and improve their overall mental health. Example papers: Human Senses, Attention Regulation
  3. Modeling Humans through Simulated Humans
    We are researching how to best resprent humans in the digital world. Make “hallucinations” a feature, not a bug. Model cognitive biases, false memories, cognitive load, frustration. etc. Make imperfect AI. How to best “represent” and “train” these imperfect features? Example papers: Negotiation
  4. Medical VQA
    We are developing advanced VQA systems that can assist healthcare professionals by providing accurate answers to complex medical questions based on medical images such as X-rays, MRIs, and CT scans. Example papers: SpineQA, VG-Galf
  5. BCI spellers
    Our lab has been developing BCI spellers for almost a decade. We worked with both SSVEP paragadigm, P300 paradigm, and hybrid paradigms. We have performed many iterative improvements on the system, including optimizing the visual stimuli, improving the signal processing and classification algorithms, and enhancing the user interface.
  6. Raman spectroscopy for non-invasive glucose monitoring
    Our lab has been working on developing a non-invasive glucose monitoring system using Raman spectroscopy. Our goal is to design and develop a portable Raman system that can help elderly and patients for glucose monitoring.