Yuyi Li

Beijing, China

Join Prog.AI to see contacts

Summary

🤩

Rockstar

🎓

Top School

Yuyi Li is a software engineer with six years of experience focused on machine learning and cross-modal analytics, based in Beijing. During a recent internship at Microsoft they worked on production-grade engineering tasks and model training pipelines, complementing academic studies in computer science at Sun Yat-sen University and a BE from Beijing University of Posts and Telecommunications. On GitHub they contribute to X-modaler, tuning training configurations and optimizers (e.g., introducing BertAdam) for image/video captioning and vision-language tasks, signaling strength in model optimization and applied research codebases. Comfortable bridging research and engineering, they excel at adapting complex ML models to diverse datasets and deployment needs. An understated plus: they favor hands-on, configuration-level improvements that make state-of-the-art cross-modal models more reliable and reproducible in practice.

6 years of coding experience

2 years of employment as a software developer

Bachelor of Engineering - BE, Computer Software Engineering, Bachelor of Engineering - BE, Computer Software Engineering at Beijing University of Posts and Telecommunications

Master's degree, Computer Science, Master's degree, Computer Science at Sun Yat-sen University

Github Skills (8)

configuration-management10

pytorch10

machine-learning10

image-text10

image-annotation10

python10

pretrain9

tensorflow8

Programming languages (2)

CPython

Github contributions (5)

YehLi/xmodaler

Aug 2021 - Oct 2022

X-modaler is a versatile and high-performance codebase for cross-modal analytics(e.g., image captioning, video captioning, vision-language pre-training, visual question answering, visual commonsense reasoning, and cross-modal retrieval).

Role in this project:

ML Engineer

Contributions:44 commits, 80 pushes, 1 branch in 1 year 2 months

Contributions summary:Yuyi's commits primarily focus on configuring and modifying training scripts for various cross-modal analytics tasks, including image captioning, video captioning, and visual question answering. The changes involve adjusting configurations for different models (e.g., GCN-LSTM, Transformer, TDEN) and datasets. They are also responsible for introducing a new optimizer, BertAdam, indicating a focus on model training and optimization within the X-modaler framework.

analyticsmodalcross-modalperformanceversatile

JDAI-CV/image-captioning

Mar 2020 - May 2021

Implementation of 'X-Linear Attention Networks for Image Captioning' [CVPR 2020]

Contributions:6 commits, 7 pushes, 14 comments in 1 year 1 month

pytorchdeep-learningimage-captioningcvpr-2020computer-vision

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.

Request Free Trial