About Me

Hi there! I am a fourth-year Ph.D. student in Computer Science at Vanderbilt University, advised by Prof. Daniel Moyer. Prior to this, I received my B.Sc. (Hons.) in Computer Science from Hong Kong Baptist University, where I was granted the Scholastic Award as one of the top 2% of graduates.

My research interests primarily lie in Generative Models, Model Inversion, Membership Inference, and Monocular Depth Estimation. I am broadly interested in adversarial attacks and defenses. My current research focuses on inverting training datasets from pre-trained generative models, specifically diffusion-based and flow-matching architectures. I am currently working on world foudnation model pre-training at Aether AI.

I am actively seeking internship opportunities for both Spring and Summer 2027. Please feel free to drop me an email at mingxing.rao@vanderbilt.edu if our research interests align, or if you would like to collaborate!

🔥 Recent News

• [Aug 2026] I will be joining Aether AI as an AI Research and Engineering Intern!
• [Jul 2026] Our paper “Score-based Membership Inference on Diffusion Models” has been accepted to Transactions on Machine Learning Research (TMLR)!
• [Jun 2026] Our paper “Generalization and Memorization in Rectified Flow” has been accepted to ECCV 2026!
• [Feb 2026] Our paper “Latent Diffusion Inversion Requires Understanding the Latent Space” has been accepted to CVPR 2026!
• [Apr 2024] Our paper “Zero-shot Prompt-based Video Encoder for Surgical Gesture Recognition” was accepted at IPCAI 2024 and published in IJCARS.

🌟 Beyond Research (Side Quests & Hobbies)

• My “Secondary Research”: I am a huge car enthusiast. I follow a lot of motorsport series, such as Formula One and the World Rally Championship. Fun driving is my ultimate stress relief. Always down to chat about anything automotive!