My name is Luchao Qi. I am passionate about exploring Machine Learning, Deep Learning (Computer Vision & Computer Graphics), and Robotics to solve real-world problems with meaningful impact. In recent years, I have worked on video generative models for various downstream tasks (see my website here for details).
Please feel free to reach out via email if you have any questions or opportunities. I’m happy to chat about research, industry roles, or life in general.
- Over++: Generative Video Compositing for Layer Interaction Effects
- EditCast3D: Single-Frame-Guided 3D Editing with Video Propagation and View Selection
- The Aging Multiverse: Generating Condition-Aware Facial Aging Tree via Training-Free Diffusion
- TalkingHeadBench: A Multi-Modal Benchmark & Analysis of Talking-Head DeepFake Detection
From: 21 February 2025 - To: 21 February 2026
Total Time: 965 hrs 19 mins
Python 586 hrs 20 mins >>>>>>>>>>>>>>>---------- 58.06 %
sh 260 hrs 3 mins >>>>>>------------------- 25.75 %
Other 44 hrs 36 mins >------------------------ 04.42 %
HTML 35 hrs 21 mins >------------------------ 03.50 %
Markdown 25 hrs 20 mins >------------------------ 02.51 %