Ron Weiss

TL;DR: This paper presented a single sequence-to-sequence ASR model trained on 9 different Indian languages, which have very little overlap in their scripts, and found that this model, which was not explicitly given any information about language identity, improved recognition performance by 21% relative compared to analogous sequence to sequence models trained on each language individually.

TL;DR: This framework enables development of complex gene circuits for engineering mammalian cells with unprecedented speed, reliability and scalability and should have broad applicability in a variety of areas including mammalian cell fermentation, cell fate reprogramming and cell-based assays.

TL;DR: In several mouse models of cancer, a single intratumoral injection of LNP-replicons eradicated large established tumors, induced protective immune memory and enabled regression of distal uninjected tumors, making them a promising multifunctional single-agent immunotherapeutic.

TL;DR: An algorithm to infer the characteristics of the sources present in a mixture is presented, allowing for significantly improved separation performance over that obtained using unadapted source models.

TL;DR: An attention-based sequence-to-sequence neural network which can directly translate speech from one language into speech in another language, without relying on an intermediate text representation is presented.