Arya Grayeli — accepted AI-conference papers

2024

Neurosymbolic Grounding for Compositional World Models

Atharva Sehgal, Arya Grayeli, Jennifer J. Sun, Swarat Chaudhuri

ICLR 2024poster

We introduce Cosmos, a framework for object-centric world modeling that is designed for compositional generalization (CompGen), i.e., high performance on unseen input scenes obtained through the composition of known visual "atoms." The central insight behind Cosmos is the use of a novel form of neur…

Cited by 7 Source ↗PDF ↗code ↗Scholar ↗

2024

Symbolic Regression with a Learned Concept Library

Arya Grayeli, Atharva Sehgal, Omar Costilla Reyes, Miles Cranmer, Swarat Chaudhuri

NeurIPS 2024poster

We present a novel method for symbolic regression (SR), the task of searching for compact programmatic hypotheses that best explain a dataset. The problem is commonly solved using genetic algorithms; we show that we can enhance such methods by inducing a library of abstract textual concepts. Our alg…

Cited by 13 Source ↗PDF ↗code ↗Scholar ↗