xiyanghu Goto Github PK

followers: 63.0 following: 39.0 repos: 36.0 gists: 0.0

Name: Xiyang (Sean) Hu

Type: User

Company: Carnegie Mellon University

Bio: PhD Student @ Carnegie Mellon University

Location: San Jose, CA

Blog: https://xiyanghu.github.io/

Hi there 👋 I'm Xiyang HU (胡曦阳 in Chinese)! <--Check out my website!

I got my Ph.D. in Information Systems at Carnegie Mellon University very soon.

🔭 I’m currently working on

the design of ML/DL models to improve accuracy/efficiency/interpretability, specifically:

Machine and Deep Learning
Data Mining
NLP
Acceleration
Open-Source Check out some of our open-source libraries/algorithms:
- PyGOD
- OSDT

the adaptation of state-of-the-art models in various social and business applications.
the understanding of the social and economic impacts of AI, e.g. fairness, human-AI.

📫 How to reach me

Email: xiyanghu [AT] cmu.edu
Twitter
WeChat(微信): dawnhxy

💬 News & Travel:

Mar 2023: Our research received AWS AI Amazon Research Award!
Jan 2022: Excited to release the first comprehensive open-sourced graph outlier detection library – PyGOD.

Xiyang (Sean) Hu's Projects

awesome-cv

:page_facing_up: Awesome CV is LaTeX template for your outstanding job application

bert_amazon_reviews

A repo to implement BERT fine tuning and classification using Amazon Review Dataset.

binoct

Binary Programming Formulation for Learning Classification Trees Using Cplex

computingbootcamp2017

Computing and reproducibility bootcamp for Duke StatSci graduate students.

data-projects

Scripts and data for various Vox Media stories and news projects

dpr

Dense Passage Retriever - is a set of tools and models for open domain Q&A task.

explainablevqa

[ACMMM Oral, 2023] "Towards Explainable In-the-wild Video Quality Assessment: A Database and a Language-Prompted Approach"

few-shot-text-classification

Few-shot binary text classification with Induction Networks and Word2Vec weights initialization

A fast, distributed, high performance gradient boosting (GBDT, GBRT, GBM or MART) framework based on decision tree algorithms, used for ranking, classification and many other machine learning tasks. It is under the umbrella of the DMTK(http://github.com/microsoft/dmtk) project of Microsoft.