Giter VIP home page Giter VIP logo

Hi there šŸ‘‹, Iā€™m Xiaoyang Song. I am currently an Industrial and Operations Engineering Ph.D. student at University of Michigan, Department of Industrial and Operations Engineering. Before, I received my M.S. degree in Data Science from Columbia University and my B.S. degree with double majors in Mathematics and Computer Science from University of Michigan. During my previous studies, I received rigorous training in computer science, mathematics, and statistics, and was fortunate to work with many distinguished research faculties from the University of Michigan on Natural Language Processing (NLP), Computer Vision (CV), and Distributed Learning.

As a passionate researcher, my goal is to explore the cuttingā€edge theories and methodologies in the fields of Machine Learning (ML), Reinforcement Learning (RL), and mathematics and apply them to Computer Vision (CV), Natural Language Processing (NLP), Transportation, Biology, Manufacturing, and other related fields in the industry. I am also deeply interested in Federated/Distributed Learning and Outā€ofā€Distribution Learning, where we made ML models more applicable by protecting the privacy of ML target users and increasing the robustness of ML models, respectively. In general, I am dedicated to deploying Machine Learning techniques into real-world applications in a robust and interpretable manner, hopefully with theoretical guarantees.

My CV can be found here. (Last Update: 12/2022)

If you are interested in contacting me, I can always be reached by email at [email protected].

Ā  Ā 

Xiaoyang Song's Projects

alphafold2 icon alphafold2

To eventually become an unofficial Pytorch implementation / replication of Alphafold2, as details of the architecture get released

cc22mw icon cc22mw

Community contributions for EDAV Fall 2022 Mon/Wed

confident_classifier icon confident_classifier

Training Confidence-Calibrated Classifier for Detecting Out-of-Distribution Samples / ICLR 2018

data-driven-analysis-of-sympatric-speciation icon data-driven-analysis-of-sympatric-speciation

This repository contains partial source codes and analysis results (including symposium presentation slides) of Xiaoyang Song's UROP research "Data-driven Analysis of Sympatric Speciation". The datasets and the source codes for our models of range overlap are kept as private at this moment. Those will be posted soon after further polishing.

deep_mahalanobis_detector icon deep_mahalanobis_detector

Code for the paper "A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks".

deepcca icon deepcca

An implementation of Deep Canonical Correlation Analysis (DCCA or Deep CCA) with pytorch.

llm-mcqa icon llm-mcqa

Overview of Large Language Model (LLM) Multiple-Choice Question-Answering (MCQA)

muzic icon muzic

Muzic: Music Understanding and Generation with Artificial Intelligence

npos icon npos

source code for ICLR'23 paper "Non-parametric Outlier Synthesis"

nyc-restaurant-inspection-database icon nyc-restaurant-inspection-database

Xiaoyang Song and Han Liu's project for NYC restaurant inspection and rating database: a web application that enables users to interactively access, modify, and browse the inspection records, food safety conditions, and informations of NYC restaurants. Additional functionalities like posting reviews and ratings are also supported.

odin icon odin

A simple and effective method for detecting out-of-distribution images in neural networks.

out-of-distribution-gans icon out-of-distribution-gans

Xiaoyang Song's Research with Dr. Wenbo Sun, Prof. Raed AI Kontar and Prof. Judy Jin from University of Michigan. This research focus on Out-of-Distribution Computer Vision data generation and detection.

rstudio-theme-customization icon rstudio-theme-customization

Xiaoyang's tutorial for RStudio editor theme customization: 1) using existing themes from Github 2) customizing your own by editing .rstheme file

themetransformer icon themetransformer

The official implementation of Theme Transformer. A Theme-based music generation. IEEE TMM

vos icon vos

source code for ICLR'22 paper "VOS: Learning What You Donā€™t Know by Virtual Outlier Synthesis"

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    šŸ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. šŸ“ŠšŸ“ˆšŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ā¤ļø Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.