11.1k citations · 16.3k across the 88 of their papers we have counts for
9 papers · 1 filter
Vectorizing string entries for data processing on tables: when are larger language models better?
Léo Grinsztajn, Edouard Oyallon, Myung Jun Kim +1
There are increasingly efficient data processing pipelines that work on vectors of numbers, for instance most machine learning models, or vector databases for fast similarity searc…
The Locality and Symmetry of Positional Encodings
Lihu Chen, Gaël Varoquaux, Fabian M. Suchanek
Positional Encodings (PEs) are used to inject word-order information into transformer-based language models. While they can significantly enhance the quality of sentence representa…
The Past, Present, and Future of the Brain Imaging Data Structure (BIDS)
Russell A. Poldrack, Christopher J. Markiewicz, Stefan Appelhoff +111
The Brain Imaging Data Structure (BIDS) is a community-driven standard for the organization of data and metadata from a growing range of neuroscience modalities. This paper is mean…
Causal thinking for decision making on Electronic Health Records: why and how
Matthieu Doutreligne, Tristan Struja, Judith Abecassis +3
Accurate predictions, as with machine learning, may not suffice to provide optimal healthcare for every patient. Indeed, prediction can be driven by shortcuts in the data, such as…
Confidence Intervals for Performance Estimates in Brain MRI Segmentation
R. El Jurdi, G. Varoquaux, O. Colliot
Medical segmentation models are evaluated empirically. As such an evaluation is based on a limited set of example images, it is unavoidably noisy. Beyond a mean performance measure…
GLADIS: A General and Large Acronym Disambiguation Benchmark
Lihu Chen, Gaël Varoquaux, Fabian M. Suchanek
Acronym Disambiguation (AD) is crucial for natural language understanding on various sources, including biomedical reports, scientific papers, and search engine queries. However, e…