UNDERGRADUATE @ FUDAN · CLASS OF 2028
Kehan LAN
Exploring how machines see, speak, and create through vision-language models and generative models.
VLMs ✦ GENERATIVE MODELS ✦ FILMS ✦ INDIE MUSIC ✦
VLMs ✦ GENERATIVE MODELS ✦ FILMS ✦ INDIE MUSIC ✦
VLMs ✦ GENERATIVE MODELS ✦ FILMS ✦ INDIE MUSIC ✦
RESEARCH MODE
Multimodal intelligence with a creative edge.
I am interested in systems that connect visual understanding, language, and generation—especially VLMs and generative models.
Enter the research archive →AFTER HOURS
Films on screen. Indie tracks on repeat.
Beyond research, I spend my time watching films and discovering indie music—the quieter signals behind the work.
Open after hours →SELECT A CHANNEL