Lasting Impact Award
The Lasting Impact Award honors the most impactful paper first published by AI2 researchers three years prior to the award date. Papers are nominated by our institute's research leaders, and the final winner is selected by our Scientific Advisory Board using several criteria, including a paper's Highly Influential Citations.
2022
From 'F' to 'A' on the N.Y. Regents Science Exams: An Overview of the Aristo Project
Peter Clark, Oren Etzioni, Daniel Khashabi, Tushar Khot, Bhavana Dalvi Mishra, Kyle Richardson, Ashish Sabharwal, Carissa Schoenick, Oyvind Tafjord, Niket Tandon, Sumithra Bhakthavatsalam, Dirk Groeneveld, Michal Guerquin, Michael SchmitzAI Magazine • 2020 AI has achieved remarkable mastery over games such as Chess, Go, and Poker, and even Jeopardy!, but the rich variety of standardized exams has remained a landmark challenge. Even in 2016, the best AI system achieved merely 59.3% on an 8th Grade science exam…
2020
Bidirectional Attention Flow for Machine Comprehension
Minjoon Seo, Aniruddha Kembhavi, Ali Farhadi, and Hannaneh HajishirziICLR • 2017 Machine comprehension (MC), answering a query about a given context paragraph, requires modeling complex interactions between the context and the query. Recently, attention mechanisms have been successfully extended to MC. Typically these methods use…
2019
XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks
Mohammad Rastegari, Vicente Ordonez, Joseph Redmon, and Ali FarhadiECCV • 2016 We propose two efficient approximations to standard convolutional neural networks: Binary-Weight-Networks and XNOR-Networks. In Binary-Weight-Networks, the filters are approximated with binary values resulting in 32x memory saving. In XNOR-Networks, both the…