Alexander Gao

Hello, I’m a research scientist at Waabi. I’m also a PhD candidate in Computer Science at the University of Maryland, College Park, where I’m advised by Ming C. Lin.

My research applies machine learning to geometric problems in computer graphics, with the goal of enabling new ways for artists and engineers to create. My interests include animation and simulation, geometry processing, geometric deep learning, and generative models for multimodal data.

I’ve interned at World Labs, Roblox, and Google, and before that worked as a software engineer at Amazon. I did my MS in Computer Science at NYU and my BA in Film Production at USC School of Cinematic Arts.

Feel free to reach out: gaoalexander@gmail.com.

Alexander Gao in Iceland
Photo by Evan Haywood

Publications

A bus at night, dark on the left and relit by the diffusion model on the right
Real-Time Diffusion Relighting as a Neural Sensor: Closing the Low-Light Domain Gap for Robotic Perception
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2026

Shengjie Xu, Alexander Gao, Anshul Rai, Dae Yeol Lee, Guan-Ming Su, and Ming C. Lin

Vector fields on a train shape, a test shape, and an error map
An Intrinsic Vector Heat Network
International Conference on Machine Learning (ICML), 2024

Alexander Gao, Maurice Chu, Mubbasir Kapadia, Ming C. Lin, and Hsueh-Ti Derek Liu

A wireframe lamp mesh and its rendering inside a radiance field
Dynamic Mesh-Aware Radiance Fields
International Conference on Computer Vision (ICCV), 2023

Alexander Gao*, Yi-Ling Qiao*, Yiran Xu, Yue Feng, Jia-Bin Huang, and Ming C. Lin

A robot building a structure of blocks from a map
Learning Simultaneous Navigation and Construction in Grid Worlds
International Conference on Learning Representations (ICLR), 2023

Wenyu Han, Haoran Wu, Eisuke Hirota, Alexander Gao, Lerrel Pinto, Ludovic Righetti, and Chen Feng

A tennis ball in a video frame and its reconstructed geometry
NeuPhysics: Editable Neural Geometry and Physics from Monocular Videos
Conference on Neural Information Processing Systems (NeurIPS), 2022

Alexander Gao*, Yi-Ling Qiao*, and Ming C. Lin

* equal contribution

Academic Service

Reviewer

NeurIPS
2023, 2025, 2026
ICML
2024
ICLR
2024
SIGGRAPH
2024
IEEE RA-L
2024