Retrieval augmentation is a powerful but expensive method to make langua...
We present our work on developing a multilingual, efficient text-to-text...
In this paper, we analyze the performance of a multitask end-to-end
tran...
Many natural language processing tasks benefit from long inputs, but
pro...
Algorithmic fairness is an essential requirement as AI becomes integrate...
Advantage Actor-critic (A2C) and Proximal Policy Optimization (PPO) are
...
Machine learning models such as Transformers or LSTMs struggle with task...
Recent work has shown that either (1) increasing the input length or (2)...
In this paper we introduce a novel algorithm called Iterative Section
Re...
Deep learning models do well at generalizing to in-distribution data but...
Several studies have reported the inability of Transformer models to
gen...
Compositional generalization is the ability to generalize systematically...
We show that Transformer encoder architectures can be massively sped up,...
Personalized adaptation technology has been adopted in a wide range of
d...
Computer games represent an ideal research domain for the next generatio...
This paper focuses on building personalized player models solely from pl...
This paper explores multi-armed bandit (MAB) strategies in very short ho...
Social comparison-based features are widely used in social computing app...
Training agents using Reinforcement Learning in games with sparse reward...
Transformers-based models, such as BERT, have been one of the most succe...
In recent years, Deep Reinforcement Learning (DRL) algorithms have achie...
Concurrent and parallel programming (CPP) is an increasingly important
s...
Transformer-based models have pushed the state of the art in many natura...
The notions of distance and similarity play a key role in many machine
l...
This paper presents a preliminary study comparing different observation ...
This paper focuses on "tracing player knowledge" in educational games.
S...
Experience Management studies AI systems that automatically adapt intera...
Games with large branching factors pose a significant challenge for game...
Levels are a key component of many different video games, and a large bo...
We introduce a novel evolutionary algorithm (EA) with a semantic
network...
Game tree search algorithms such as minimax have been used with enormous...
Analogy plays an important role in creativity, and is extensively used i...