Hi, my name is Wei. I'm exploring
generative multimedia computing.
I’m a computer science researcher focusing on multimedia computing. I’m currently interested in building data-driven, generative models involving multiple modalities, e.g. synthesizing audio signal from visual cues. I propel my research with one general problem: what creates perception?
I approach my problem from an inter-disciplinary perspective mixing vision, graphics, natural language processing and neuroscience. My ultimate goal is to generate diverse and high-fidelity multimedia contents that allow intuitive editing to fit production needs.
On this site, I post thoughts, notes and reports over various topics related to my works. You can read most of them in my research and blogs.
In my spare time I enjoy: long-distance running, writing, traveling.