Dongting Hu

12/2024: We release of SnapGen Paper on Arxiv, first image generation model (379M) that can synthesize high-resolution images (1024x1024) on mobile devices in 1.4s, and achieve 0.66 on GenEval metric.
09/2024: Congrats to our 3D editting paper was accepted to NeurIPS 2024.
08/2024: I joined Snap Inc. as an reseach Intern.

An AI researcher and a photographer.
An explorer and a traveller.

About

Hi! I am Dongting Hu, a final-year Ph.D. candidate in the School of Mathematics and Statistics at the University of Melbourne, advised by Dr. Mingming Gong, co-advised by Dr. Liuhua Peng, and Dr. Tingjin Chu. I am a member of the Melbourne Deep Learning Group.

I interned at Snap Research Creative Vision, working on efficient text-to-image generative models with Dr. Yanwu Xu, Dr. Anil Kag, and Dr. Jian Ren.

My research interests lie in generative AI and its applications to various computer vision tasks, with a focus on:

Large-scale Multimodal Generative Models
3D Vision
Efficient AIGC

I am seeking industrial positions starting Fall 2025. Feel free to reach out via email (timmy11hu AT gmail.com) if there are opportunities aligned with my expertise.