Neurosymbolic Grounding for Compositional World Models

no code implementations • 19 Oct 2023 • Atharva Sehgal, Arya Grayeli, Jennifer J. Sun, Swarat Chaudhuri

We introduce Cosmos, a framework for object-centric world modeling that is designed for compositional generalization (CG), i. e., high performance on unseen input scenes obtained through the composition of known visual "atoms."

Neurosymbolic Programming for Science

no code implementations • 10 Oct 2022 • Jennifer J. Sun, Megan Tjandrasuwita, Atharva Sehgal, Armando Solar-Lezama, Swarat Chaudhuri, Yisong Yue, Omar Costilla-Reyes

Neurosymbolic Programming (NP) techniques have the potential to accelerate scientific discovery.

Composing Neural Learning and Symbolic Reasoning with an Application to Visual Discrimination

1 code implementation • 12 Jul 2019 • Adithya Murali, Atharva Sehgal, Paul Krogmeier, P. Madhusudan

We consider the problem of combining machine learning models to perform higher-level cognitive tasks with clear specifications.

Few-Shot Learning