0
点赞
收藏
分享

微信扫一扫

AI 前沿编程实习社 2022-06 月刊

Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding

​​Chitwan Saharia​​​, ​​William Chan​​​, ​​Saurabh Saxena​​​, ​​Lala Li​​​, ​​Jay Whang​​​, ​​Emily Denton..​​

​​PDF​​

​​​Search​​​​Scholar​​

​Summary

Imagen builds on the power of large transformer language models in understanding text. It hinges on the strength of diffusion models in high-fidelity image generation. Imagen achieves a new state-of-the-art FID score of 7.27 on the COCO dataset.

​​AI 前沿编程实习社 2022-06 月刊_deeplearning​​​​​​​​AI 前沿编程实习社 2022-06 月刊_deeplearning_02​​​​AI 前沿编程实习社 2022-06 月刊_paper_03​​​​AI 前沿编程实习社 2022-06 月刊_paper_04​​

Published on Tue May 24 2022


Large Language Models are Zero-Shot Reasoners

​​Takeshi Kojima​​​, ​​Shixiang Shane Gu​​​, ​​Machel Reid​​​, ​​Yutaka Matsuo​​​, ​​Yusuke Iwasawa​​

​​PDF ​​

​​​Search​​​​Scholar​​

Summary

Pretrained large language models (LLMs) are widely used in many sub-fields of natural language processing (NLP) These successes are often attributed to LLMs' ability for few-shot learning. We show that LLMs are decent zero-shot reasoners by simply adding Let's think step by step'' before each answer.​​AI 前沿编程实习社 2022-06 月刊_deeplearning_05​​​​AI 前沿编程实习社 2022-06 月刊_paper_06​​​​AI 前沿编程实习社 2022-06 月刊_deeplearning_07​​​​AI 前沿编程实习社 2022-06 月刊_paper_08​​​​AI 前沿编程实习社 2022-06 月刊_paper_09​​​


Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models

​​Aarohi Srivastava​​​, ​​Abhinav Rastogi​​​, ​​Abhishek Rao​​​, ​​Abu Awal Md Shoeb​​​, ​​Abubakar Abid​​​, ​​Adam Fisch​​ ...

​​PDF​​

​​​Search​​​​Scholar​​

Summary

Language models demonstrate both quantitative improvement and new qualitative capabilities with increasing scale. Despite their potentially transformative impact, these new capabilities are as yet poorly characterized. To address this challenge, we introduce the Beyond the Imitation Game benchmark (BIG-bench)

​​AI 前沿编程实习社 2022-06 月刊_paper_10​​​​AI 前沿编程实习社 2022-06 月刊_paper_11​​​​AI 前沿编程实习社 2022-06 月刊_paper_12​​​​AI 前沿编程实习社 2022-06 月刊_paper_13​​​​AI 前沿编程实习社 2022-06 月刊_deeplearning_14​​


Toward a realistic model of speech processing in the brain with self-supervised learning

​​Juliette Millet​​​, ​​Charlotte Caucheteux​​​, ​​Pierre Orhan​​​, ​​Yves Boubenec​​​, ​​Alexandre Gramfort​​​, ​​Ewan Dunbar​​, See More ...

​​PDF​​

​​​Search​​​​Scholar​​

Summary

       Several deep neural networks have recently been shown to generate activations similar to those of the brain in response to the same input. These algorithms, however, remain largely implausible. We hypothesize that self-supervised algorithms trained on the raw waveform constitute a promising candidate.

​​AI 前沿编程实习社 2022-06 月刊_deeplearning_15​​​​AI 前沿编程实习社 2022-06 月刊_deeplearning_16​​​​ ​​​​AI 前沿编程实习社 2022-06 月刊_deeplearning_17​​

举报

相关推荐

2022-04-06

0 条评论