Xiaohan Zou
Teaching Assistant at Penn State University
Bethlehem, Pennsylvania, United States
Summary
🤩
Rockstar🎓
Top SchoolXiaohan Zou is a PhD student and teaching assistant at Penn State with eight years of experience building ML-driven systems and front-end prototypes. They bridge research and engineering—contributing to multimodal foundation models as a research assistant while previously developing efficient continual-learning algorithms and video-text retrieval pipelines at industry labs like Kuaishou and Oracle. Xiaohan’s hands-on work spans PyTorch model engineering, Keras-based speech emotion recognition, and React/UnoCSS UI projects (including a macOS-like portfolio with interactive controls), showing comfort across stack and domain. Known for publishing and presenting novel meta-learning methods, they combine rigorous academic training from Penn State, Boston University, and Tongji with pragmatic code delivery. A playful “dragon lost in human world” on GitHub hints at a creative, experimental approach to problem solving.
8 years of coding experience
3 years of employment as a software developer
Bachelor of Engineering - BE, Software Engineering, Bachelor of Engineering - BE, Software Engineering at Tongji UniversityDoctor of Philosophy - PhD, Computer Science and Engineering, Doctor of Philosophy - PhD, Computer Science and Engineering at Penn State UniversityMaster of Science - MS, Computer Science, Master of Science - MS, Computer Science at Boston University
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (18)
python10
machine-learning10
svm10
typescript10
vite10
mlp10
mask-rcnn10
keras10
lstm10
typescript-types10
unocss10
faster-rcnn10
typescripts10
librosa10
react10
Programming languages (7)
Github contributions (5)
Renovamen/playground-macos
Apr 2021 - Dec 2022
My portfolio website simulating macOS's GUI, developed with React and UnoCSS.
Role in this project:
Front-end Developer
Front-end DeveloperContributions:178 commits, 3 PRs, 144 pushes in 1 year 7 months
Contributions summary:Xiaohan implemented a basic playground simulating macOS's GUI, building a control center menu and other UI components. The code changes involved the creation of a control center menu and other UI elements, incorporating features such as display settings, sound control, and a music player. These changes used React and UnoCSS to align with the portfolio website's description. Furthermore, the changes reflect the user's ability to apply libraries like `react-rangeslider` and integrate components like `Webcam` for added functionality.
reacttailwindcssviteguiredux
Renovamen/Speech-Emotion-Recognition
Apr 2019 - Apr 2022
Speech emotion recognition implemented in Keras (LSTM, CNN, SVM, MLP) | 语音情感识别
Role in this project:ML Engineer
ML EngineerContributions:2 releases, 58 commits, 65 pushes in 3 years
Contributions summary:Xiaohan primarily focused on implementing and integrating various machine-learning models for speech emotion recognition. Their work involved the development of CNN, LSTM, and MLP models, as well as the integration of an SVM model. Key contributions include the training and evaluation of these models and the integration of the Librosa library for feature extraction and Opensmile. The user also added features such as waveform and spectrogram visualization.
emotion-recognitionmlpemotionsvmdeep-learning
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.