Search Results for author: Krishna Dubba

Found 2 papers, 1 papers with code

Grounding Natural Language Instructions: Can Large Language Models Capture Spatial Information?

1 code implementation17 Sep 2021 Julia Rozanova, Deborah Ferreira, Krishna Dubba, Weiwei Cheng, Dell Zhang, Andre Freitas

Even though BERT and similar pre-trained language models have excelled in several NLP tasks, their use has not been widely explored for the UI grounding domain.

SCRAM: Spatially Coherent Randomized Attention Maps

no code implementations24 May 2019 Dan A. Calian, Peter Roelants, Jacques Cali, Ben Carr, Krishna Dubba, John E. Reid, Dell Zhang

The central idea of SCRAM is to employ PatchMatch, a randomized correspondence algorithm, to quickly pinpoint the most compatible key (argmax) for each query first, and then exploit that knowledge to design a sparse approximation to non-local mean operations.

Cannot find the paper you are looking for? You can Submit a new open access paper.