Xianghao Kong

I’m currently a Video GenAI Researcher at Voia. I was a CS Ph.D. student, worked with the incredible ✨ Prof. Greg Ver Steeg ✨ at the University of California, Riverside. Fortunately, I also worked at SonyAI(Host: Vikash Sehwag) and Adobe Firefly (Host: Hareesh Ravi) as a Research Intern.

My research centers on Generative Models (Diffusion Models & Energy-Based Models), with a focus on their interpretability, alignment, and compositionality. Specifically, I explore diffusion models through a novel information-theoretic lens, termed Information-Theoretic Diffusion (ITD) ℹ️. Our work demonstrates how Pointwise Mutual Information (PMI) enhances compositional reasoning and modality alignment (e.g., text and image). We are actively expanding the ITD universe 🌌 and welcome collaboration opportunities!

Prior to UCR, I focused on EEG data analysis in Brain-Computer Interface (BCI) 🧠 technology, bridging neuroscience and computer science. Outside of research, I enjoy exploring food, sketching, and visiting museums.