Andrew N. Carr
Brigham Young University
5 Papers
1 Citations
Andrew N. Carr is an academic researcher from Brigham Young University. The author has contributed to research in topics: Computer science & Permutation. The author has an hindex of 2, co-authored 5 publications.
Chat about Author
Papers
•Posted Content
Evaluating Large Language Models Trained on Code
Mark Chen,Jerry Tworek,Heewoo Jun,Qiming Yuan,Henrique Ponde de Oliveira Pinto,Jared Kaplan,Harrison Edwards,Yuri Burda,Nicholas Joseph,Greg Brockman,Alex Ray,Raul Puri,Gretchen Krueger,Michael Petrov,Heidy Khlaaf,Girish Sastry,Pamela Mishkin,Brooke Chan,Scott Gray,Nick Ryder,Mikhail Pavlov,Alethea Power,Lukasz Kaiser,Mohammad Bavarian,Clemens Winter,Philippe Tillet,Felipe Petroski Such,Dave Cummings,Matthias Plappert,Fotios Chantzis,Elizabeth A. Barnes,Ariel Herbert-Voss,William H. Guss,Alex Nichol,Alex Paino,Nikolas Tezak,Jie Tang,Igor Babuschkin,Suchir Balaji,Shantanu Jain,William Saunders,Christopher Hesse,Andrew N. Carr,Jan Leike,Joshua Achiam,Vedant Misra,Evan Morikawa,Alec Radford,Matthew M. Knight,Miles Brundage,Mira Murati,Katie Mayer,Peter Welinder,Bob McGrew,Dario Amodei,Samuel McCandlish,Ilya Sutskever,Wojciech Zaremba +57 more
TL;DR: Codex as discussed by the authors is a GPT language model fine-tuned on publicly available code from GitHub, and study its Python code-writing capabilities, showing that repeated sampling from the model is a surprisingly effective strategy for producing working solutions to difficult prompts.
1K
•Posted Content
Graph Neural Processes: Towards Bayesian Graph Neural Networks.
Andrew N. Carr,David Wingate +1 more
TL;DR: Graph Neural Processes (GNP) is introduced, inspired by the recent work in conditional and latent neural processes, and the ability to extend graph neural networks to inputs of dynamic sized graphs.
15
•Posted Content
Wasserstein Neural Processes.
TL;DR: It is shown that there are desirable classes of problems where NPs, with this loss of maximum likelihood, fail to learn any reasonable distribution, and this drawback is solved by using approximations of Wasserstein distance.
1
Self-Supervised Learning of Audio Representations From Permutations With Differentiable Ranking
TL;DR: In this article, a model was proposed to reorder shuffled parts of the spectrogram of an audio signal to improve downstream classification performance, which was shown to improve instrument classification and pitch estimation.
Self-Supervised Learning of Audio Representations from Permutations with Differentiable Ranking
TL;DR: In this paper, a pre-trained model is used to reorder shuffled parts of the spectrogram of an audio signal to improve downstream classification performance, and the authors show that inverting permutations is a meaningful pretext task for learning audio representations.