Recent news

  • VideoMLA was accepted to NeurIPS 2026. [Paper]
  • I am officially on the job market! Completing my Ph.D. in Spring 2027 and actively seeking full-time Research Scientist/Engineer roles in generative AI, video and image generation, and foundation models. [Resume]
  • Completed a research internship at Waymo working on open-vocabulary 3D perception.

All news →

Seeking Research Scientist / Engineer Roles • Spring 2027

Ph.D. candidate at Virginia Tech completing in Spring 2027. Seeking full-time roles in generative AI, video and image generation, and foundation models.

Resume → • Download CV (PDF) • [email protected] • LinkedIn • Google Scholar • GitHub

I am a Ph.D. candidate in Computer Science at Virginia Tech, advised by Prof. Pinar Yanardag. My research focuses on representation steering for generative foundation models to make image and video synthesis controllable and computationally efficient. Recent work covers long-horizon video diffusion, spherical flow matching, and mechanistic interpretability.

Before my Ph.D., I spent six years building production machine learning systems. I owned cloud serving infrastructure for generative models processing over 5M requests daily, deployed personalization pipelines for thousands of daily users, and developed full-stack computer vision training and evaluation platforms from scratch.

Selected research

View all publications