Yen-cheng Liu
Member Of Technical Staff at Microsoft AI
Mountain View, California, United States
Summary
👤
Senior🎓
Top SchoolYen-cheng Liu is a research-oriented machine learning engineer with a decade of experience focused on computer vision and making large-scale models more efficient in parameters, data, and labels. Currently a Member of Technical Staff at Microsoft AI after research roles at Meta and a PhD from Georgia Tech, he has driven advances in few-shot, semi-supervised, and parameter-efficient adaptation methods with publications at ICLR, CVPR, ECCV, and NeurIPS. His work includes pioneering multi-agent collaborative perception and cutting training costs—once cutting trainable parameters by 90% for dense vision adaptation—while also exploring robust, communication-aware inference across models. Based in Mountain View, he blends deep academic rigor with practical industry impact, often translating novel research into scalable solutions for generative and multi-modal vision systems.
10 years of coding experience
8 years of employment as a software developer
Bachelor of Science (B.Sc.) Electrical and Computer Engineering, Bachelor of Science (B.Sc.) Electrical and Computer Engineering at National Chiao Tung UniversityMaster of Science - MS Graduate Institute of Electrical Engineering, Master of Science - MS Graduate Institute of Electrical Engineering at National Taiwan UniversityDoctor of Philosophy - PhD Machine Learning, Doctor of Philosophy - PhD Machine Learning at Georgia Institute of TechnologyErasmus Program Electrical Engineering and Information Technology, Erasmus Program Electrical Engineering and Information Technology at Technical University of Munich
Chinese, English
Github Skills (19)
semantic-segmentation9
multiagent-systems9
multi-agent8
pytorch7
graph7
deep-learning7
agent7
computer-vision7
object-detection7
perception5
meta-learning5
classification5
semi-supervised-learning4
supervised-learning4
image-classification3
Programming languages (1)
Github contributions (5)
facebookresearch/unbiased-teacher
Feb 2021 - Jul 2021
PyTorch code for ICLR 2021 paper Unbiased Teacher for Semi-Supervised Object Detection
Contributions:7 commits, 6 pushes, 62 comments in 5 months
pytorchiclrsupervisedteachersemi
GT-RIPL/MultiAgentPerception
Jun 2020 - Jun 2022
Official source code to CVPR'20 paper, "When2com: Multi-Agent Perception via Communication Graph Grouping"
Contributions:9 commits, 2 PRs, 6 pushes in 2 years
multi-agent-systemspytorchmulti-agent-perceptionmultiagent-reinforcement-learningagent
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.