Hanrong Ye
Research Scientist at NVIDIA
United States
Summary
👤
Senior🎓
Top SchoolHanrong Ye is a Research Scientist specializing in computer vision and machine learning with a decade of experience and an active research trajectory spanning top industry labs. Currently at NVIDIA, Hanrong focuses on multi-modal and large-scale foundation models, building on internships at Apple, Adobe, and a prior NVIDIA stint where they worked on any-to-any modality LLMs and egocentric video multi-modality models. Their PhD work at HKUST, combined with earlier studies at Peking University and Sun Yat-sen University, grounds a strong theoretical background in addition to applied research. Hanrong is comfortable bridging low-level vision tasks like panoptic and instance segmentation with high-level generative and multimodal model design, and often works at the intersection of video, audio, image, and language modalities. Colleagues describe them as someone who pairs rigorous academic training with fast iteration in industrial research settings.
11 years of coding experience
Dongguan Tungwah High SchoolComputer Applied Technology, Computer Applied Technology at Peking UniversitySchool of Physics, School of Physics at Sun Yat-sen UniversityHong Kong University of Science and Technology (HKUST)
English, Chinese, Chinese
Github Skills (72)
feature-engineering10
depth-estimation10
model-compression10
hyperparameter-tuning10
neural-architecture-search10
pascal10
nas10
automated-machine-learning10
multi-task-learning10
segmentation10
machine-learning-algorithms9
python9
3d-object-detection9
deep-learning9
hyperparameter-optimization9
Programming languages (6)
Github contributions (5)
prismformore/expAT
Jun 2020 - Mar 2021
TIP: Bi-directional Exponential Angular Triplet Loss for RGB-Infrared Person Re-Identification
Contributions:18 commits, 13 pushes, 7 comments in 9 months
angularre-identificationperson-reidentificationcomputer-visionpytorch
prismformore/SDSEN
May 2019 - May 2020
Contributions:16 commits, 3 pushes in 1 year
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.