2021

Learning Transferable Visual Models From Natural Language Supervision

Applies task-agnostic, web-scale pre-training to computer vision using natural language supervision, enabling powerful zero-shot transfer to many datasets.

Embodied Intelligence via Learning and Evolution

Large-scale evolutionary simulations by DERL yield insights into how the interaction between learning, evolution, and environmental complexity can lead to morphological intelligence.

Learning the Predictability of the Future

Presents the idea of using hyperbolic embeddings for hierarchical representations and provides some experiments classifying action within a hierarchy of actions.