Yong Zhong
Machine Learning · Representation Learning · Parameter Generation
SUSTech · NUS
Yong Zhong is a rising senior in Computer Science at Southern University of Science and Technology (SUSTech). His research interests include machine learning, representation learning, and parameter generation.
I am currently a visiting student at the National University of Singapore, advised by Dr. Kai Wang and Prof. Yang You, working at the intersection of diffusion language models, large language models, and parameter generation. Previously, I worked with Prof. Feng Zheng on embodied AI and robotic data generation at SUSTech.
latest posts
A New Home for My Notes
Rebuilding this site as a durable home for technical notes and projects.
1 min read · 2026Cross-Entropy、KL、NLL 与 MLE:同一个目标的四种写法
从一个统一目标出发,推导 cross-entropy、forward KL divergence、negative log-likelihood 与 maximum likelihood estimation 的关系及成立条件。
3 min read · 2026证据下界的推导和解释 What Can We Know from ELBO?
从 importance sampling 和 Jensen's inequality 出发推导 ELBO,并解释它在 VAE 中的两种形式。
1 min read · 2026