Hello! I'm Sky.

An undergraduate researcher interested in natural language processing and situated communication.


Research Assistant @ EAGLe Lab (Professor Joyce Chai)
Research Assistant @ Blablablab (Professor David Jurgens)
Previously @ SRG (Professors Arunesh Sinha & Michael Wellman), NASA (GSFC-610.2), and Microsoft (Azure IoT - Infrastructure).


Interests (broadly): Grounding, situated dialogue, computational sociolinguistics, linguistic variation and diachronic change, machine theory of mind, reinforcement learning, game theory, adversarial learning, pragmatics. (a lot, I know)


profile

Sky CH. Wang
University of Michigan, Ann Arbor, MI
B.S.E in Computer Science
College of Engineering
Sep 2017 — Dec 2020 (Expected)


About Me | Publications | Experience | Honors/Awards | Contact

LinkedIn | Github


🦄 Site Periodically Updated 🦄



About Me

Back to Main
profile

Washington D.C. | 北京 | Ann Arbor

🇺🇸 🇨🇳 〽️


Hello! I'm Sky.

With a focus on natural language processing, my research aims to make advances on creating more efficient, more effective, and more robust linguistic communication policies, with a long-term goal of bulding smarter, more personalized agents.

My current research projects focus on situated human-agent communication and computational sociolinguistics.

(@EAGLe Lab) I'm interested in looking at how to build agents 🤖 that think 🤔 like humansTM, communicate with humans, and that are able to learn efficiently from humans and other agents. In this regard, grounded, situated language learning and machine theory of mind are areas of particular interest to me. How do humans communicate with each other in coorperative or adversarial scenarios? In times of uncertainty? How is communication predictive of actions, and can we incorporate these ideas in building better, more efficient agents?

(@Blablablab) Looking at how language 🤬 itself is reflective of society's beliefs and values, and how such norms have evolved over time is, too, an area of intrigue. What causes these shifts in cultural norms, who 👪 are the most affected, and how can we best capture these changes? Here, computational sociolinguistics comes into play. In particular, I'm looking at how & where social perceptions of gender and sexuality have evolved over time, the disparities that exist, and their sources of change.

(@SRG) Previously, I focused on adversarial robustness and reinforcement learning. There, I looked at creating more robust 💪 and more modular defenses against adversarial attacks, and on creating more sample efficient ⏩ learning methods for agents with combinatorial action spaces.

Publications



Publications

Back to Main

Papers

A Learning and Masking Approach to Secure Learning
9th International Conference on Decision and Game Theory for Security 2018
Linh Nguyen, Sky Wang, Arunesh Sinha

...and three more papers currently under review / in preprint status (check back later 🤗!)

Extended Abstracts

Enriching the Twitter Stream: Increasing Data Mining Yield and Quality Using Machine Learning
American Geophysical Union 2018 Fall Meeting
William Teng, Arif Albayrak, John Corcoran, Sky Wang, Daniel Maksumov, Carlee Loeser, Long Pham

Working Drafts

Using Sociolinguistic Variables to Reveal Changing Attitudes Towards Sexuality and Gender
Under Review
Sky Wang, David Jurgens

Social Precipitation Sensing
Preprint
Sky Wang, Arif Albayrak, William Teng, Long Pham

Building Action Sets in a Deep Reinforcement Learner
Preprint
Yongzhao Wang, Arunesh Sinha, Sky Wang, Michael Wellman





Experience

Back to Main

Research

Research Assistant (EAGLe Lab)
September 2019—Present
University of Michigan—Ann Arbor, MI

Research Assistant (Blablablab)
September 2019—Present
University of Michigan—Ann Arbor, MI

Research Assistant (SRG)
September 2017—April 2019
University of Michigan—Ann Arbor, MI

Research Intern (GSFC-610.2)
June 2018—August 2018
NASA—Greenbelt, MD

Research Intern (Astronomy)
June 2014—August 2014
Caltech—Pasadena, CA

Industry

Software Engineering Intern (Azure IoT Infrastructure)
June 2019—August 2019
Microsoft—Redmond, WA

Full Stack Web Developer
March 2017—September 2017
Teconet—Beijing, CN

Entrepreneurial

Founder & CEO
March 2013—February 2016
SkyCraft—Beijing, CN

Courses (@Michigan)

EECS 692
Advanced Artificial Intelligence

EECS 598
Situated Language Processing for Embodied AI Agents

EECS 598
Human-Computer Interaction

EECS 498
Multidisciplinary Software Development

EECS 492
Introduction to Artificial Intelligence

EECS 484
Database Management Systems

EECS 445
Introduction to Machine Learning

EECS 442
Computer Vision

EECS 376
Foundations of Computer Science

EECS 370
Introduction to Computer Organization

EECS 281
Data Structures & Algorithms

EECS 203
Discrete Math

MATH 216
Introduction to Differential Equations

MATH 215
Multvariable & Vector Calculus

MATH 214
Applied Linear Algebra







Honors & Awards

Back to Main

Best Course Project, EECS 442 Computer Vision (Fall 2019 w. David Fouhey)
Awarded to 3/?? final course projects.

Best Poster, University of Michigan Artificial Intelligence Symposium 2018
Awarded to 2/44 posters.

Dean's Honor List, Fall 2017—Present (All Semesters)
"For high scholastic standing and outstanding achievements."

University Honors, Fall 2017-Present (All Semesters)
"For distinguished academic achievements."





Contact

Back to Main

phone: (734) 773 2165

e-mail: skywang AT umich.edu