YerevaNN /jɛɾɛvɑnˈɛn/ is a non-profit machine learning research lab based in Yerevan, Armenia.
about our plans to establish an AI Institute.
Machine learning for biomedical data
Machine learning under domain shift
Machine learning algorithms
-  Identifying and disentangling spurious features in pretrained image representations.
(with Meta AI and USC ISI).
Accepted at ICML 2023 Workshop on Spurious Correlations, Invariance and Stability.
-  Characterization of the failure modes of domain generalization algorithms.
Published in CVPR'22
(with USC ISI).
-  Robust classification under class-dependent domain shift
(with USC ISI). Presented at ICML 2020
Development of Armenian treebanks
The handwritten digits in the background are generated by deep convolutional generative adversarial networks [paper] [code]
-  Scaling laws for mixed-modal language models.
(with Meta AI)
-  Wireless non-line-of-sight localization of a device using a single antenna in an urban environment
Accepted at IEEE Big Data Service 2023.
(with Yerevan State University and
CNR Institute of Informatics and Telematics)
-  Matching map recovery with an unknown number of outliers.
Published in AISTATS'23
-  GradSkip: an extension of a local gradient method for distributed
optimization that supports variable number of local gradient steps in each communication round.
-  WARP: a parameter-efficient method for transfer learning in NLP.
Published in ACL'21
(with USC ISI)
-  Theoretical analysis of the detection of the feature matching map in presence of outliers.
Published in Electronic Journal of Statistics
-  A survey of deep neural networks for semi-supervised image classification.
Published in JUCS.
-  A novel robust estimator of the mean of a multivariate Gaussian distribution.
Published in Annals of Statistics
-  T-Corex: a novel method for temporal covariance estimation using information theoretic apparatus
(with USC ISI)