Santiago Ontañón

research

∙ 08/28/2023

MEMORY-VQ: Compression for Tractable Internet-Scale Memory

Retrieval augmentation is a powerful but expensive method to make langua...

0 Yury Zemlyanskiy, et al. ∙

research

∙ 05/18/2023

mLongT5: A Multilingual and Efficient Text-To-Text Transformer for Longer Sequences

We present our work on developing a multilingual, efficient text-to-text...

0 David Uthus, et al. ∙

research

∙ 05/08/2023

Multi-Task End-to-End Training Improves Conversational Recommendation

In this paper, we analyze the performance of a multitask end-to-end tran...

0 Naveen Ram, et al. ∙

research

∙ 03/17/2023

CoLT5: Faster Long-Range Transformers with Conditional Computation

Many natural language processing tasks benefit from long inputs, but pro...

0 Joshua Ainslie, et al. ∙

research

∙ 02/18/2023

Improving Fairness in Adaptive Social Exergames via Shapley Bandits

Algorithmic fairness is an essential requirement as AI becomes integrate...

0 Robert C. Gray, et al. ∙

research

∙ 05/18/2022

A2C is a special case of PPO

Advantage Actor-critic (A2C) and Proximal Policy Optimization (PPO) are ...

11 Shengyi Huang, et al. ∙

research

∙ 03/28/2022

LogicInference: A New Dataset for Teaching Logical Inference to seq2seq Models

Machine learning models such as Transformers or LSTMs struggle with task...

0 Santiago Ontañón, et al. ∙

research

∙ 12/15/2021

LongT5: Efficient Text-To-Text Transformer for Long Sequences

Recent work has shown that either (1) increasing the input length or (2)...

0 Mandy Guo, et al. ∙

research

∙ 11/12/2021

Identifying On-road Scenarios Predictive of ADHD usingDriving Simulator Time Series Data

In this paper we introduce a novel algorithm called Iterative Section Re...

0 David Grethlein, et al. ∙

research

∙ 10/08/2021

Iterative Decoding for Compositional Generalization in Transformers

Deep learning models do well at generalizing to in-distribution data but...

0 Luana Ruiz, et al. ∙

research

∙ 08/09/2021

Making Transformers Solve Compositional Tasks

Several studies have reported the inability of Transformer models to gen...

0 Santiago Ontañón, et al. ∙

research

∙ 06/19/2021

Improving Compositional Generalization in Classification Tasks via Structure Annotations

Compositional generalization is the ability to generalize systematically...

0 Juyong Kim, et al. ∙

research

∙ 05/09/2021

FNet: Mixing Tokens with Fourier Transforms

We show that Transformer encoder architectures can be massively sped up,...

0 James Lee-Thorp, et al. ∙

research

∙ 03/02/2021

The Personalization Paradox: the Conflict between Accurate User Models and Personalized Adaptive Systems

Personalized adaptation technology has been adopted in a wide range of d...

0 Santiago Ontañón, et al. ∙

research

∙ 02/15/2021

Player-Centered AI for Automatic Game Personalization: Open Problems

Computer games represent an ideal research domain for the next generatio...

0 Jichen Zhu, et al. ∙

research

∙ 02/10/2021

Player Modeling via Multi-Armed Bandits

This paper focuses on building personalized player models solely from pl...

0 Robert C. Gray, et al. ∙

research

∙ 02/10/2021

Regression Oracles and Exploration Strategies for Short-Horizon Multi-Armed Bandits

This paper explores multi-armed bandit (MAB) strategies in very short ho...

0 Robert C. Gray, et al. ∙

research

∙ 01/25/2021

Personalization Paradox in Behavior Change Apps: Lessons from a Social Comparison-Based Personalized App for Physical Activity

Social comparison-based features are widely used in social computing app...

0 Jichen Zhu, et al. ∙

research

∙ 10/05/2020

Action Guidance: Getting the Best of Sparse Rewards and Shaped Rewards for Real-time Strategy Games

Training agents using Reinforcement Learning in games with sparse reward...

0 Shengyi Huang, et al. ∙

research

∙ 07/28/2020

Big Bird: Transformers for Longer Sequences

Transformers-based models, such as BERT, have been one of the most succe...

72 Manzil Zaheer, et al. ∙

research

∙ 06/25/2020

A Closer Look at Invalid Action Masking in Policy Gradient Algorithms

In recent years, Deep Reinforcement Learning (DRL) algorithms have achie...

8 Shengyi Huang, et al. ∙

research

∙ 05/10/2020

Understanding Learners' Problem-Solving Strategies in Concurrent and Parallel Programming: A Game-Based Approach

Concurrent and parallel programming (CPP) is an increasingly important s...

0 Jichen Zhu, et al. ∙

research

∙ 04/17/2020

ETC: Encoding Long and Structured Data in Transformers

Transformer-based models have pushed the state of the art in many natura...

46 Joshua Ainslie, et al. ∙

research

∙ 02/18/2020

An Overview of Distance and Similarity Functions for Structured Data

The notions of distance and similarity play a key role in many machine l...

0 Santiago Ontañón, et al. ∙

research

∙ 10/26/2019

Comparing Observation and Action Representations for Deep Reinforcement Learning in MicroRTS

This paper presents a preliminary study comparing different observation ...

0 Shengyi Huang, et al. ∙

research

∙ 08/15/2019

Tracing Player Knowledge in a Parallel Programming Educational Game

This paper focuses on "tracing player knowledge" in educational games. S...

0 Pavan Kantharaju, et al. ∙

research

∙ 07/04/2019

Experience Management in Multi-player Games

Experience Management studies AI systems that automatically adapt intera...

0 Jichen Zhu, et al. ∙

research

∙ 10/13/2017

Combinatorial Multi-armed Bandits for Real-Time Strategy Games

Games with large branching factors pose a significant challenge for game...

0 Santiago Ontañón, et al. ∙

research

∙ 06/23/2016

The VGLC: The Video Game Level Corpus

Levels are a key component of many different video games, and a large bo...

0 Adam James Summerville, et al. ∙

research

∙ 04/30/2014

A semantic network-based evolutionary algorithm for computational creativity

We introduce a novel evolutionary algorithm (EA) with a semantic network...

0 Atilim Gunes Baydin, et al. ∙

research

∙ 08/09/2012

Experiments with Game Tree Search in Real-Time Strategy Games

Game tree search algorithms such as minimax have been used with enormous...

0 Santiago Ontañón, et al. ∙

research

∙ 04/11/2012

Automated Generation of Cross-Domain Analogies via Evolutionary Computation

Analogy plays an important role in creativity, and is extensively used i...

0 Atilim Gunes Baydin, et al. ∙

Santiago Ontañón

Featured Co-authors