4 papers
Epiplexity Guided Data Selection and Generation for Out-of-Distribution Generalization
Ellen Su, Andres Potapczynski, Shikai Qiu +2
Modern systems are increasingly expected to transfer across tasks not specified during training. What data facilitates generalization in these new, unanticipated settings? One hypo…
Opinion: Learning Intuitive Physics May Require More than Visual Data
Ellen Su, Solim Legris, Todd M. Gureckis +1
Humans expertly navigate the world by building rich internal models founded on an intuitive understanding of physics. Meanwhile, despite training on vast quantities of internet vid…
MOTIVE: A Drug-Target Interaction Graph For Inductive Link Prediction
John Arevalo, Ellen Su, Anne E Carpenter +1
Drug-target interaction (DTI) prediction is crucial for identifying new therapeutics and detecting mechanisms of action. While structure-based methods accurately model physical int…
Extracting Memorized Training Data via Decomposition
Ellen Su, Anu Vellore, Amy Chang +4
The widespread use of Large Language Models (LLMs) in society creates new information security challenges for developers, organizations, and end-users alike. LLMs are trained on la…