Zobrazeno 1 - 10
of 232
pro vyhledávání: '"Schaerli, P."'
Publikováno v:
Nature Communications, Vol 15, Iss 1, Pp 1-13 (2024)
Abstract Oscillations are a recurrent phenomenon in biological systems across scales, but deciphering their fundamental principles is very challenging. Here, we tackle this challenge by redesigning the wellcharacterised synthetic oscillator known as
Externí odkaz:
https://doaj.org/article/90d53740d35e4244ba4f860144d3bd90
Large language models (LLMs) have achieved impressive performance on code generation. However, for complex programming tasks, generating the correct solution in one go becomes challenging, thus some prior works have designed program repair approaches
Externí odkaz:
http://arxiv.org/abs/2304.05128
Autor:
Shi, Freda, Chen, Xinyun, Misra, Kanishka, Scales, Nathan, Dohan, David, Chi, Ed, Schärli, Nathanael, Zhou, Denny
Large language models have achieved impressive performance on various natural language processing tasks. However, so far they have been evaluated primarily on benchmarks where all information in the input context is relevant for solving the task. In
Externí odkaz:
http://arxiv.org/abs/2302.00093
Autor:
Suzgun, Mirac, Scales, Nathan, Schärli, Nathanael, Gehrmann, Sebastian, Tay, Yi, Chung, Hyung Won, Chowdhery, Aakanksha, Le, Quoc V., Chi, Ed H., Zhou, Denny, Wei, Jason
BIG-Bench (Srivastava et al., 2022) is a diverse evaluation suite that focuses on tasks believed to be beyond the capabilities of current language models. Language models have already made good progress on this benchmark, with the best model in the B
Externí odkaz:
http://arxiv.org/abs/2210.09261
Autor:
Drozdov, Andrew, Schärli, Nathanael, Akyürek, Ekin, Scales, Nathan, Song, Xinying, Chen, Xinyun, Bousquet, Olivier, Zhou, Denny
Humans can reason compositionally when presented with new tasks. Previous research shows that appropriate prompting techniques enable large language models (LLMs) to solve artificial compositional generalization tasks such as SCAN. In this work, we i
Externí odkaz:
http://arxiv.org/abs/2209.15003
Autor:
Amélie Cabirol, Audam Chhun, Joanito Liberti, Lucie Kesner, Nicolas Neuschwander, Yolanda Schaerli, Philipp Engel
Publikováno v:
mSphere, Vol 9, Iss 9 (2024)
ABSTRACT The study of the fecal microbiota is crucial for unraveling the pathways through which gut symbionts are acquired and transmitted. While stable gut microbial communities are essential for honey bee health, their modes of acquisition and tran
Externí odkaz:
https://doaj.org/article/c576936be02943ecba5e50970c2e6dd3
Autor:
Zhou, Denny, Schärli, Nathanael, Hou, Le, Wei, Jason, Scales, Nathan, Wang, Xuezhi, Schuurmans, Dale, Cui, Claire, Bousquet, Olivier, Le, Quoc, Chi, Ed
Chain-of-thought prompting has demonstrated remarkable performance on various natural language reasoning tasks. However, it tends to perform poorly on tasks which requires solving problems harder than the exemplars shown in the prompts. To overcome t
Externí odkaz:
http://arxiv.org/abs/2205.10625
Autor:
Anne-Stéphanie Rueff, Renske van Raaphorst, Surya D. Aggarwal, Javier Santos-Moreno, Géraldine Laloux, Yolanda Schaerli, Jeffrey N. Weiser, Jan-Willem Veening
Publikováno v:
Nature Communications, Vol 14, Iss 1, Pp 1-12 (2023)
Abstract Phenotypic variation is the phenomenon in which clonal cells display different traits even under identical environmental conditions. This plasticity is thought to be important for processes including bacterial virulence, but direct evidence
Externí odkaz:
https://doaj.org/article/e8c7dfd4d89b4c2a9b32de5868db46ec
Autor:
Audam Chhun, Silvia Moriano-Gutierrez, Florian Zoppi, Amélie Cabirol, Philipp Engel, Yolanda Schaerli
Publikováno v:
PLoS Biology, Vol 22, Iss 3 (2024)
Externí odkaz:
https://doaj.org/article/08be4feea5cc41af94233457dd05c985
Autor:
Tsarkov, Dmitry, Tihon, Tibor, Scales, Nathan, Momchev, Nikola, Sinopalnikov, Danila, Schärli, Nathanael
We present *-CFQ ("star-CFQ"): a suite of large-scale datasets of varying scope based on the CFQ semantic parsing benchmark, designed for principled investigation of the scalability of machine learning systems in a realistic compositional task settin
Externí odkaz:
http://arxiv.org/abs/2012.08266