trophy

I am a PhD candidate 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 using techniques from HCI and visualization to help people better understand and improve their AI systems. I am supported by an NSF Graduate Research Fellowship and have spent time at Apple AI/ML, Microsoft Research, & Google.

March 21, 2024

I successfully defended my thesis 🎉.

March 1, 2024

We launched <|endoftext|>, an AI-powered prompt editor.

January 10, 2024

Our evals of Google's Gemini models was featured by TechCrunch & VentureBeat.

HCOMP'23

Where Does My Model Underperform? A Human Evaluation of Slice Discovery Algorithms

Nari Johnson, Ángel Alexander Cabrera, Gregory Plumb, Ameet Talwalkar

Best Paper

TMLR

Towards a More Rigorous Science of Blindspot Discovery in Image Classification Models

Gregory Plumb*, Nari Johnson*, Ángel Alexander Cabrera, Ameet Talwalkar

CHI'23

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

CSCW'23

Improving Human-AI Collaboration with Descriptions of AI Behavior

Ángel Alexander Cabrera, Adam Perer, Jason I. Hong

TOCHI'22

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

CHI'22

Symphony: Composing Interactive Interfaces for Machine Learning

Ángel Alexander Cabrera*, Alex Bäuerle*, Fred Hohman, Megan Maher, David Koski, Xavier Suau, Titus Barik, Dominik Moritz

PNAS'21

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]

CSCW'21

Discovering and Validating AI Errors With Crowdsourced Failure Reports

Ángel Alexander Cabrera, Abraham Druck, Jason I. Hong, Adam Perer

NeurIPS'20

Regularizing Black-box Models for Improved Interpretability

Gregory Plumb, Maruan Al-Shedivat, Ángel Alexander Cabrera, Adam Perer, Eric Xing, Ameet Talwalkar

CSCW'20

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

VIS'19

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

Preprint, 2023

An In-depth Look at Gemini's Language Abilities

Syeda Nahida Akter, Zichun Yu, Aashiq Muhamed, Tianyue Ou, Alex Bäuerle, Ángel Alexander Cabrera, Krish Dholakia, Chenyan Xiong, Graham Neubig

Workshop, ICML'22

Evaluating Systemic Error Detection Methods using Synthetic Images

Gregory Plumb, Nari Johnson, Ángel Alexander Cabrera, Marco Tulio Ribeiro, Ameet Talwalkar

Workshop, CHI'20

"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

Workshop, ICLR'19

Discovery of Intersectional Bias in Machine Learning Using Automatic Subgroup Generation

Ángel Alexander Cabrera, Minsuk Kahng, Fred Hohman, Jamie Morgenstern, Duen Horng (Polo) Chau

Demo, CVPR'18

Interactive Classification for Deep Learning Interpretation

Ángel Alexander Cabrera, Fred Hohman, Jason Lin, Duen Horng (Polo) Chau