activity
20172022
most citedRECAST: Enabling User Recourse and Interpretability of Toxicity Detection Models with Interactive Visualization

31 citations · 99 across the 13 of their papers we have counts for

collaborators

17 papers

cs.HC2022

NeuroMapper: In-browser Visualizer for Neural Network Training

Zhiyan Zhou, Kevin Li, Haekyu Park +4

We present our ongoing work NeuroMapper, an in-browser visualization tool that helps machine learning (ML) developers interpret the evolution of a model during training, providing…

cs.SI2022

Explaining Website Reliability by Visualizing Hyperlink Connectivity

Seongmin Lee, Sadia Afroz, Haekyu Park +5

As the information on the Internet continues growing exponentially, understanding and assessing the reliability of a website is becoming increasingly important. Misinformation has…

cs.CV2021

NeuroCartography: Scalable Automatic Visual Summarization of Concepts in Deep Neural Networks

Haekyu Park, Nilaksh Das, Rahul Duggal +4

Existing research on making sense of deep neural networks often focuses on neuron-level interpretation, which may not adequately capture the bigger picture of how concepts are coll…

econ.GN20211 cited

Quantifying the Impact of Human Capital, Job History, and Language Factors on Job Seniority with a Large-scale Analysis of Resumes

Austin P Wright, Caleb Ziems, Haekyu Park +4

As job markets worldwide have become more competitive and applicant selection criteria have become more opaque, and different (and sometimes contradictory) information and advice i…

cs.HC202131 cited

RECAST: Enabling User Recourse and Interpretability of Toxicity Detection Models with Interactive Visualization

Austin P Wright, Omar Shaikh, Haekyu Park +5

With the widespread use of toxic language online, platforms are increasingly using automated systems that leverage advances in natural language processing to automatically flag and…

cs.CV2021

SkeletonVis: Interactive Visualization for Understanding Adversarial Attacks on Human Action Recognition Models

Haekyu Park, Zijie J. Wang, Nilaksh Das +4

Skeleton-based human action recognition technologies are increasingly used in video based applications, such as home robotics, healthcare on aging population, and surveillance. How…