Ángel  Alex ander  Cabrera

I am a PhD student in the Human-Computer Interaction Institute (HCII) at Carnegie Mellon University, advised by Adam Perer and Jason Hong. I work on human-centered AI, specifically in applying techniques from HCI and visualization to help people better understand and improve their machine learning models. I am supported by an NSF Graduate Research Fellowship and have spent time at Apple AI/ML, Microsoft Research, and Google.

Education

2019 - Present
Ph.D. in Human-Computer Interaction (HCI)
Carnegie Mellon University

Advised by Adam Perer and Jason Hong.

2022
M.S. in Human-Computer Interaction
Carnegie Mellon University
2019
B.S. in Computer Science
Georgia Institute of Technology

Concentration in intelligence and modeling/simulation. Minor in economics.

Fall 2017
Sciences Po - Paris, France

Exchange program with a focus on economics and political science.

Work Experience

Summer 2021
Apple AI/ML
Research Intern

Modular machine learning interfaces, see Symphony.

Summer 2020
Microsoft Research
Research Intern

Behavioral model analysis, see AIFinnity.

Summer 2018
Google
Software Engineering Intern

Automated driver assistance and hyperlocal weather prediction for Android Auto.

Summer 2017
Google
Software Engineering Intern

Anomaly detection and regression analysis system for Google's data processing pipelines.

Summer 2016
Google
Engineering Practicum Intern

Analytics platform for monitoring and detecting erroneous edits to Google Maps.

Awards

2023
Mozilla Technology Fund

$50,000 grant to develop Zeno as an auditing tool for AI.

2023
Stanford HAI Audit Challenge

Zeno was a finalist for the HAI challenge for designing better AI auditing tools.

2019 - 2022
National Science Foundation Graduate Research Fellowship (NSF GRFP)

Three-year graduate fellowship for independent research. Full tuition with an annual stipend of $34,000.

2019
Love Family Foundation Scholarship

Co-awarded the $10,000 scholarship for the undergraduate with the most outstanding scholastic record.

2015 - 2019
Stamps President's Scholar
Georgia Tech and the Stamps Family Charitable Foundation

Full ride scholarship with $15,000 in extracurricular funding awarded to 10 incoming students.

2018
The Data Open Datathon
Correlation One and Citadel Securities

Placed third and won $2,500 for creating a ML system to predict dangerous road areas.

Refereed Publications

[11]
Where Does My Model Underperform? A Human Evaluation of Slice Discovery Algorithms
Nari Johnson, Ángel Alexander Cabrera, Gregory Plumb, Ameet Talwalkar

AAAI Conference on Human Computation and Crowdsourcing (HCOMP). Delft, Netherlands, 2023.

[10]
Towards a More Rigorous Science of Blindspot Discovery in Image Classification Models
Gregory Plumb*, Nari Johnson*, Ángel Alexander Cabrera, Ameet Talwalkar

Transactions on Machine Learning Research (TMLR). 2023.

[9]
Zeno: An Interactive Framework for Behavioral Evaluation of Machine Learning
Ángel Alexander Cabrera, Erica Fu, Donald Bertucci, Kenneth Holstein, Ameet Talwalkar, Jason I. Hong, Adam Perer

ACM Conference on Conference on Human Factors in Computing Systems (CHI). Hamburg, Germany, 2023.

[8]
Improving Human-AI Collaboration with Descriptions of AI Behavior
Ángel Alexander Cabrera, Adam Perer, Jason I. Hong

ACM Conference on Computer-Supported Cooperative Work and Social Computing (CSCW). Minneapolis, 2023.

[7]
What Did My AI Learn? How Data Scientists Make Sense of Model Behavior
Ángel Alexander Cabrera, Marco Tulio Ribeiro, Bongshin Lee, Rob DeLine, Adam Perer, Steven M. Drucker

ACM Transactions on Computer-Human Interaction (TOCHI). 2023.

[6]
Symphony: Composing Interactive Interfaces for Machine Learning
Ángel Alexander Cabrera*, Alex Bäuerle*, Fred Hohman, Megan Maher, David Koski, Xavier Suau, Titus Barik, Dominik Moritz

ACM Conference on Conference on Human Factors in Computing Systems (CHI). New Orleans, 2022.

[5]
An open repository of real-time COVID-19 indicators
Alex Reinhart, Logan Brooks, Maria Jahja, Aaron Rumack, Jingjing Tang, [et al, including Ángel Alexander Cabrera]

Proceedings of the National Academy of Sciences (PNAS). 2021.

[4]
Discovering and Validating AI Errors With Crowdsourced Failure Reports
Ángel Alexander Cabrera, Abraham Druck, Jason I. Hong, Adam Perer

ACM Conference on Computer-Supported Cooperative Work and Social Computing (CSCW). Virtual, 2021.

[3]
Regularizing Black-box Models for Improved Interpretability
Gregory Plumb, Maruan Al-Shedivat, Ángel Alexander Cabrera, Adam Perer, Eric Xing, Ameet Talwalkar

Conference on Neural Information Processing Systems (NeurIPS). Vancouver, 2020.

[2]
Designing Alternative Representations of Confusion Matrices to Support Non-Expert Public Understanding of Algorithm Performance
Hong Shen, Haojian Jin, Ángel Alexander Cabrera, Adam Perer, Haiyi Zhu, Jason I. Hong

ACM Conference on Computer-Supported Cooperative Work and Social Computing (CSCW). Virtual, 2020.

[1]
FairVis: Visual Analytics for Discovering Intersectional Bias in Machine Learning
Ángel Alexander Cabrera, Will Epperson, Fred Hohman, Minsuk Kahng, Jamie Morgenstern, Duen Horng (Polo) Chau

IEEE Conference on Visual Analytics Science and Technology (VAST). Vancouver, Canada, 2019.

Workshops, Demos, Posters, and Preprints

[4]
Evaluating Systemic Error Detection Methods using Synthetic Images
Gregory Plumb, Nari Johnson, Ángel Alexander Cabrera, Marco Tulio Ribeiro, Ameet Talwalkar

ICML - Workshop on Spurious Correlations, Invariance and Stability. Baltimore, MD, 2022.

[3]
"Public(s)-in-the-Loop": Facilitating Deliberation of Algorithmic Decisions in Contentious Public Policy Domains
Hong Shen, Ángel Alexander Cabrera, Adam Perer, Jason I. Hong

CHI - Fair & Responsible AI Workshop. Hawaii, USA, 2020.

[2]
Discovery of Intersectional Bias in Machine Learning Using Automatic Subgroup Generation
Ángel Alexander Cabrera, Minsuk Kahng, Fred Hohman, Jamie Morgenstern, Duen Horng (Polo) Chau

ICLR - Debugging Machine Learning Models Workshop (Debug ML). New Orleans, Louisiana, USA, 2019.

[1]
Interactive Classification for Deep Learning Interpretation
Ángel Alexander Cabrera, Fred Hohman, Jason Lin, Duen Horng (Polo) Chau

CVPR - Demo. Salt Lake City, Utah, USA, 2018.

Talks

2022, 2023
Evaluating Machine Learning

CMU 05-618/318: Human-AI Interaction
CMU 10-605/805: ML with Large Datasets
CMU 17-634: Applied Machine Learning

2022
Visualization and Machine Learning

CMU 17-428/728: ML and Sensing

2022
Designing Large Web Applications

CMU 05-431/631: Software Structures for User Interfaces (SSUI)

2022
Modern Web Frameworks

CMU 05-431/631: Software Structures for User Interfaces (SSUI)

2021
Ethics in Data Visualization

CMU 05-899: Data Visualization

2021
D3 Deep Dive

CMU 05-899: Data Visualization

2021
Data Science Widgets with Svelte and Jupyter

Svelte Summit 2021

Teaching

Fall 2022
05-431/631: Software Structures for User Interfaces (SSUI)
Graduate Teaching Assistant @ Carnegie Mellon

Teach weekly lab sections, grade tests and homeworks.

Fall 2021
05-499:C: Data Visualization
Graduate Teaching Assistant @ Carnegie Mellon

Taught a D3 course and led an ethics workshop in addition to grading and course management.

2016 - 2018
CS1332: Data Structures and Algorithms
Undergraduate Teaching Assistant @ Georgia Tech

Taught a weekly recitation, graded tests and homework, and helped create assignments.

Mentoring

Spring 2023
- Summer 2023
Steven Huang
Research Associate, Carnegie Mellon

Chart builder for Zeno.

Spring 2023 - Present
Josh Zhou
B.S. in Computer Science, Carnegie Mellon

Instance tagging for Zeno.

Fall 2022 -
Present
Tianqi Wu
M.S. in Computer Science, Carnegie Mellon

Interactive slice discovery for Zeno.

Summer 2022 - Present
Erica Fu
B.S. in Information Systems, Carnegie Mellon

UX design for an ML evaluation platform. See Zeno.

Summer 2022 - Present
Donny Bertucci
B.S. in Computer Science, Oregon State University. REU at Carnegie Mellon

Interactive model debugging. See Zeno.

Summer 2022
Kan Sun
B.S. in Math, Carnegie Mellon.

Algorithmic discovery of ML errors.

Fall 2021
- Spring 2022
Emily Guo
B.S. in Statistics and Machine Learning, Carnegie Mellon

Improving human-AI interaction with descriptions of model behavior.

Spring 2020
- Spring 2021
Abraham Druck
B.S. in Mathematical Sciences, Carnegie Mellon. Now: Technology Analyst at Morgan Stanely

Crowdsourced discovery of ML failures for image captioning. See Deblinder.

2020
CMU AI Mentoring Program

Service

Program Committee
2022 - 2023
AC, ACM Conference on Human Factors in Computing Systems (CHI) Late Breaking Work
2022 - 2023
PC, ACM Fairness, Accountability, and Transparency (FAccT)
2022 - 2023
PC, IEEE VIS Workshop on Visualization for AI Explainability (VISxAI)
2023
Organizer, CSCW Workshop on Supporting User Engagement in Testing, Auditing, and Contesting AI
2023
PC, CHI Workshop on Trust and Reliance in AI-Assisted Tasks (TRAIT)
2022
AC, ACM Conference on Computer-Supported Cooperative Work and Social Computing (CSCW) Posters
Reviewer
2021 - 2023
ACM Conference on Human Factors in Computing Systems (CHI)
2021 - 2023
ACM Conference on Computer-Supported Cooperative Work and Social Computing (CSCW)
2020 - 2023
IEEE VIS
2022 - 2023
ACM Fairness, Accountability, and Transparency (FAccT)
2022
ACM Symposium on User Interface Software and Technology (UIST)
2022
IEEE Computer Graphics and Applications (CGASI)
2019 - 2021
IEEE Transactions on Visualization and Computer Graphics (TVCG)
2019
ACM Transactions on Interactive Intelligent Systems (TiiS)
Student Volunteer
2019
IEEE VIS
2019
ACM Fairness, Accountability, and Transparency (FAccT)
Department
2022 - 2023
REU application reviewer
2020 - 2021
Ph.D. student faculty representative

Press

2023
"Auditing AI: Announcing the 2023 Mozilla Technology Fund Cohort" - Mozilla
2020
"New forecasting data could help public health officials prepare for what's next in the coronavirus pandemic" - CNN
2020
"Facebook and Google Survey Data May Help Map Covid-19's Spread" - Wired
2020
"Carnegie Mellon Unveils Five Interactive COVID-19 Maps" - Carnegie Mellon
2020
"Visualizing Fairness in Machine Learning" - Data Stories Podcast
2019
"Alex Cabrera Wins Love Family Foundation Scholarship" - GT SCS
2019
"Georgia Tech Satellite Successfully Launched Into Space " - Georgia Tech
2018
"Datathon Challenges Students to Create Solutions to Real-World Problems" - GT SCS

Projects and Open Source

2023
Zeno

An interactive ML evaluation framework for any data or model.

2021
Svelte + Vega

A Svelte component for reactively rendering Vega and Vega-Lite visualizations.

2021
Svelte + Jupyter Widgets

A framework for creating reactive data science widgets using Svelte JS.

2020
COVIDCast Visualization of COVID-19 Indicators

Interactive visualization system of COVID-19 indicators gathered through >20,000,000 surveys on Facebook and Google by CMU Delphi.

2015 - 2017
PROX-1 Satellite
Flight Software Lead and Researcher

Led a team of engineers in developing the software for a fully undergraduate-led satellite mission.

2014
CTF Resources

Guide and resources for capture the flag (CTF) competitions with over 1.6k stars on GitHub.

Selected Courses

Ph.D.
MultiModal Machine Learning
Causality and Machine Learning
Human Judgement and Decision Making
Applied Research Methods
B.S.
Deep Learning
Data and Visual Analytics
Machine Learning
Computer Simulation
Honors Algorithms