Skip to main content ->
Ai2

Research - Papers

Explore a selection of our published work on a variety of key research challenges in AI.

Filter papers

DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Experts

Alisa LiuMaarten SapXiming LuYejin Choi
2021
ACL

Despite recent advances in natural language generation, it remains challenging to control attributes of generated text. We propose DExperts: Decoding-time Experts, a decoding-time method for… 

GridTools: A framework for portable weather and climate applications

AfanasyevA.M. Biancoand T. C. Schulthess
2021
Elsevier

Weather forecasts and climate projections are of tremendous importance for economical and societal reasons. Software implementing weather and climate models is complex to develop and hard to… 

MULTIMODALQA: COMPLEX QUESTION ANSWERING OVER TEXT, TABLES AND IMAGES

Alon TalmorOri YoranAmnon CatavJonathan Berant
2021
ICLR

When answering complex questions, people can seamlessly combine information from visual, textual and tabular sources. While interest in models that reason over multiple pieces of evidence has surged… 

DeLighT: Deep and Light-weight Transformer

Sachin MehtaMarjan GhazvininejadSrini IyerHannaneh Hajishirzi
2021
ICLR

We introduce a very deep and light-weight transformer, DeLighT, that delivers similar or better performance than transformer-based models with significantly fewer parameters. DeLighT more… 

Pushing it out of the Way: Interactive Visual Navigation

Kuo-Hao ZengLuca WeihsA. FarhadiR. Mottaghi
2021
arXiv

We have observed significant progress in visual navigation for embodied agents. A common assumption in studying visual navigation is that the environments are static; this is a limiting assumption.… 

CODE: COMPILER-BASED NEURON-AWARE ENSEMBLE TRAINING

E. TrainitiThanapon NorasetDavid DemeterSimone Campanoni
2021
Proceedings of Machine Learning and Systems

Deep Neural Networks (DNNs) are redefining the state-of-the-art performance in a variety of tasks like speech recognition and image classification. These impressive results are often enabled by… 

Searching for Scientific Evidence in a Pandemic: An Overview of TREC-COVID

Kirk RobertsTasmeer AlamSteven BedrickW. Hersh
2021
arXiv

We present an overview of the TREC-COVID Challenge, an information retrieval (IR) shared task to evaluate search on scientific literature related to COVID-19. The goals of TREC-COVID include the… 

Improving the Accessibility of Scientific Documents: Current State, User Needs, and a System Solution to Enhance Scientific PDF Accessibility for Blind and Low Vision Users

Lucy Lu WangIsabel CacholaJonathan BraggDaniel S. Weld
2021
arXiv

The majority of scientific papers are distributed in PDF, which pose challenges for accessibility, especially for blind and low vision (BLV) readers. We characterize the scope of this problem by… 

ManipulaTHOR: A Framework for Visual Object Manipulation

Kiana EhsaniWinson HanAlvaro HerrastiR. Mottaghi
2021
arXiv

The domain of Embodied AI has recently witnessed substantial progress, particularly in navigating agents within their environments. These early successes have laid the building blocks for the… 

Bootstrapping Relation Extractors using Syntactic Search by Examples

Matan EyalAsaf AmramiHillel Taub-TabibYoav Goldberg
2021
EACL

The advent of neural-networks in NLP brought with it substantial improvements in supervised relation extraction. However, obtaining a sufficient quantity of training data remains a key challenge. In…