Hyelin Nam

I'm an AI Research Engineer at EverEx. Before joining EverEx, I completed my master's at KAIST, where I was advised by Jong Chul Ye.

Recently, I have worked on diffusion models, leveraging their adaptability to enhance the quality of generated outputs. My goal is to advance generative models to accurately capture real-world dynamics, ultimately enabling them to function as reliable real-world priors.

Email  /  CV  /  Scholar  /  Github  /  Blog (Korean)

Research

A text-to-3D method using a video generation model to jointly generate diverse camera poses and realistic 3DGS for unbounded scenes.

A zero-shot inference-time steering method that enhances geometric alignment in 3D/4D scene generation by integrating scene reconstruction using pose-free geometric reward functions.

Prompt optimization driven by an optical flow discriminator to enhance temporal consistency and natural motion dynamics in video diffusion models.

A simple fix to CFG that enables lower guidance scales, improves sample quality and invertibility.

Ensure structural correspondence by leveraging diffusion features during the score distillation process.