2 citations · 2 across the 1 of their papers we have counts for
6 papers
Position: Use Sparse Autoencoders to Discover Unknowns
Kenny Peng, Rajiv Movva, Jon Kleinberg +2
While sparse autoencoders (SAEs) have generated significant excitement, a series of negative results have added to skepticism about their usefulness. Here, we establish a conceptua…
Inferring fine-grained migration patterns across the United States
Gabriel Agostini, Rachel Young, Maria Fitzpatrick +2
Fine-grained migration data illuminate demographic, environmental, and health phenomena. However, United States migration data have serious drawbacks: public data lack spatial gran…
Urban Incident Prediction with Graph Neural Networks: Integrating Government Ratings and Crowdsourced Reports
Sidhika Balachandar, Shuvom Sadhuka, Bonnie Berger +2
Graph neural networks (GNNs) are widely used in urban spatiotemporal forecasting, such as predicting infrastructure problems. In this setting, government officials wish to know in…
Sparse Autoencoders for Hypothesis Generation
Rajiv Movva, Kenny Peng, Nikhil Garg +2
We describe HypotheSAEs, a general method to hypothesize interpretable relationships between text data (e.g., headlines) and a target variable (e.g., clicks). HypotheSAEs has three…
Learning Disease Progression Models That Capture Health Disparities
Erica Chiang, Divya Shanmugam, Ashley N. Beecy +4
Disease progression models are widely used to inform the diagnosis and treatment of many progressive diseases. However, a significant limitation of existing models is that they do…
Bayesian Modeling of Zero-Shot Classifications for Urban Flood Detection
Matt Franchi, Nikhil Garg, Wendy Ju +1
Street scene datasets, collected from Street View or dashboard cameras, offer a promising means of detecting urban objects and incidents like street flooding. However, a major chal…