Exploiting Invariance in Training Deep Neural Networks. Proceedings of the AAAI Conference on Artificial Intelligence, 2022.
Network deconvolution. The International Conference on Learning Representations (ICLR) 2020 (spotlight paper).
The sea lamprey germline genome provides insights into programmed genome rearrangement and vertebrate evolution. Nature Genetics, 2018.
DBG2OLC: efficient assembly of large genomes using long erroneous reads of the third generation sequencing technologies. Scientific reports, 2016.
LightNet: A Versatile, Standalone Matlab-based Environment for Deep Learning. Proceedings of the 2016 ACM on Multimedia Conference, 2016.
BlindCall: ultra-fast base-calling of high-throughput sequencing data by blind deconvolution. Bioinformatics, 2014.
Exploiting sparseness in de novo genome assembly. BMC bioinformatics, 2012.
Background
Research interests: Deep Learning, Computer Vision, Bioinformatics. Currently a software engineer at Google DeepMind, focusing on ultra-efficient machine learning with applications to large language models (LLMs).