Intelligence relies on an agent's knowledge of what it does not know. This capability can be
assessed based on the quality of joint predictions of labels across multiple inputs. In …

Reinforcement learning agents have demonstrated remarkable achievements in simulated
environments. Data efficiency poses an impediment to carrying this success over to real …

Learning a sequence of tasks without access to iid observations is a widely studied form of
continual learning (CL) that remains challenging. In principle, Bayesian learning directly …

High-quality recommender systems ought to deliver both innovative and relevant content
through effective and exploratory interactions with users. Yet, supervised learning-based …

A multi-task learning (MTL) system aims at solving multiple related tasks at the same time.
With a fixed model capacity, the tasks would be conflicted with each other, and the system …

Thompson sampling (TS) is a popular heuristic for action selection, but it requires sampling
from a posterior distribution. Unfortunately, this can become computationally intractable in …

We present evidence of substantial benefit from efficient exploration in gathering human
feedback to improve large language models. In our experiments, an agent sequentially …

Motivated by the intuitive understanding humans have about the space of possible
interactions, and the ease with which they can generalize this understanding to previously …

Language models can learn a range of capabilities from unsupervised training on text
corpora. However, to solve a particular problem (such as text summarization) it is typically …

Recent developments in few-shot learning have shown that during fast adaption, gradient-
based meta-learners mostly rely on embedding features of powerful pretrained networks …