An-chieh Cheng
Research Scientist Intern at UC San Diego
San Diego, California, United States
Summary
👤
Senior🎓
Top SchoolAn-chieh Cheng is a PhD candidate at UC San Diego and a research scientist intern at NVIDIA, with a decade of experience building multimodal foundation models focused on spatial understanding and actionable intelligence. Advised by Prof. Xiaolong Wang, he blends rigorous academic research with industry experience from internships at Adobe and Appier to push models toward real-world perception and interaction. His work targets generalizable spatial reasoning across modalities, aiming to make models not just descriptive but operationally useful. Based in San Diego, he brings a systems-minded approach informed by strong foundations in computer science and information systems from National Tsing Hua University. Notably, his profile reflects a consistent trajectory of translating research prototypes into applied ML systems within top-tier research and product teams.
10 years of coding experience
1 year of employment as a software developer
University of California, San DiegoMaster's degree, Information Systems and Applications, Master's degree, Information Systems and Applications at National Tsing Hua University
English
Github Skills (29)
automl9
neural-architecture-search9
multi-objective-optimization8
survey8
scene-graph8
simulations7
hdr-image7
tensorflow7
value-iteration7
convolution6
markov-decision-processes6
3d6
language-model6
pytorch6
robotics6
Programming languages (3)
Github contributions (5)
AnjieCheng/CanonicalVAE
Jul 2022 - Sep 2022
[ECCV'22] This repository is the implementation of "Autoregressive 3D Shape Generation via Canonical Mapping".
Contributions:25 commits, 4 pushes, 1 comment in 2 months
3d
AnjieCheng/InstaNAS
May 2019 - May 2021
[AAAI'20][ICML'19 AutoML] This repository is the implementation of "InstaNAS: Instance-aware Neural Architecture Search"
Contributions:15 commits, 6 pushes in 1 year 11 months
automlneural-architecture-searchinstanas
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.