Researchers often rely on humans to code (label, annotate, etc.) large s...
A rapidly increasing amount of human conversation occurs online. But
div...
While large language models (LLMs) like GPT-3 have achieved impressive
r...
We explore the idea of compressing the prompts used to condition languag...
We propose and explore the possibility that language models can be studi...
Pre-trained language models derive substantial linguistic and factual
kn...
Large natural language models (such as GPT-3 or T5) demonstrate impressi...
It is notoriously difficult to control the behavior of artificial neural...
Human teams are able to easily perform collaborative manipulation tasks....
In the multi-objective reinforcement learning (MORL) paradigm, the relat...
Neural Processes (NPs) are a class of models that learn a mapping from a...
We predict future video frames from complex dynamic scenes, using an
inv...
We introduce Graph Neural Processes (GNP), inspired by the recent work i...
As autonomous agents become more ubiquitous, they will eventually have t...
Classic grammars and regular expressions can be used for a variety of
pu...
Intelligent systems sometimes need to infer the probable goals of people...
Autonomous agents must often detect affordances: the set of behaviors en...
We present a new algorithm for approximate inference in probabilistic
pr...
Models of dynamical systems based on predictive state representations (P...
We present the Infinite Latent Events Model, a nonparametric hierarchica...