One-way lectures are ineffective. What if we can transform any lecture video into a dialogue between a virtual learner and instructor? We present VIVID, an LLM-powered system that made this possible.
Project website๐: https://t.co/7bGv2XkJ5n
Preprint๐: https://t.co/A5H9tHMrbn
๐ข Do you frequently participate in online discussions? Do you try to change the opinions of others in discussions? Please share your experiences and challenges with us and receive a $8 gift card.
๐Interested? Fill out the form: https://t.co/Ao89LLzvtt
At #CHI2024 today @igules8925 will present VIVID, a system that enables instructors to transform their lecture videos into vicarious dialogs with control. Itโs a cool tool! Itโs also her first CHI and first talk. Super proud!
If you are interested in results and technical details, please check out our paper!
This work was done with my amazing collaborators, Hyewon, Yoonjoo(@yoonjoo_le2 ), and Juho(@imjuhokim ). Also, I really appreciate KIXLAB (@kixlab_kaist) members who gave me helpful feedback.
One-way lectures are ineffective. What if we can transform any lecture video into a dialogue between a virtual learner and instructor? We present VIVID, an LLM-powered system that made this possible.
Project website๐: https://t.co/7bGv2XkJ5n
Preprint๐: https://t.co/A5H9tHMrbn
Lastly, our work introduces interesting discussion points:
How can we enhance the design of human-AI interaction in an authoring system like VIVID?
In what ways can VIVID be seamlessly integrated into video lectures to enhance online learnersโ experiences and learning outcomes?
I always tell my students: if you only read paper published in the past five years, the probability that you will have any ground-breaking idea in your lifetime is nearly zero. The odds is probably less than winning a jackpot on a slot machine in Vegas...